catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-03-11 17:21:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Enhance UX and Coordinator Role Constraints in Skills Documentation

Browse Source 
- Added detailed constraints for the Coordinator role in the team UX improvement skill, emphasizing orchestration responsibilities and workflow management.
- Updated test cases in DashboardToolbar, useIssues, and useWebSocket to improve reliability and clarity.
- Introduced new tests for configStore and ignore patterns in Codex Lens to ensure proper functionality and configuration handling.
- Enhanced smart search functionality with improved embedding selection logic and added tests for various scenarios.
- Updated installation and usage documentation to reflect changes in directory structure and role specifications.
This commit is contained in:
catlog22
2026-03-08 23:43:44 +08:00
parent f3ae78f95e
commit 61ea9d47a6
110 changed files with 1516 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
.codex/skills/team-arch-opt/SKILL.md
View File

@@ -658,3 +658,41 @@ All agents (csv-wave and interactive) share a single `discoveries.ndjson` file f
8. **Max 3 Fix Cycles**: Review-fix cycle capped at 3 iterations; escalate to user after
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

2
.codex/skills/team-arch-opt/instructions/agent-instruction.md
View File

@@ -3,7 +3,7 @@
### MANDATORY FIRST STEPS
1. Read shared discoveries: {session_folder}/discoveries.ndjson (if exists, skip if not)
2. Read project context: .workflow/project-tech.json (if exists)
3. Read task schema: .codex/skills/team-arch-opt/schemas/tasks-schema.md
3. Read task schema: ~ or <project>/.codex/skills/team-arch-opt/schemas/tasks-schema.md
---

42
.codex/skills/team-brainstorm/SKILL.md
View File

@@ -233,7 +233,7 @@ const clarifier = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-brainstorm/agents/topic-clarifier.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-brainstorm/agents/topic-clarifier.md (MUST read first)
2. Read: .workflow/project-tech.json (if exists)
---
@@ -478,7 +478,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-brainstorm/agents/gc-controller.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-brainstorm/agents/gc-controller.md (MUST read first)
2. Read: ${sessionFolder}/discoveries.ndjson (shared discoveries)
---
@@ -685,3 +685,41 @@ When the challenger returns critique results with severity-graded verdicts:
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-coordinate/SKILL.md
View File

@@ -627,3 +627,41 @@ See `instructions/agent-instruction.md` for the base instruction template that i
8. **Dynamic Roles**: All worker roles are generated at runtime from task analysis -- no static role registry
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

40
.codex/skills/team-designer/SKILL.md
View File

@@ -595,7 +595,7 @@ All agents (csv-wave and interactive) share a single `discoveries.ndjson` file f
**Format**: One JSON object per line (NDJSON):
```jsonl
{"ts":"2026-03-08T10:00:00Z","worker":"SCAFFOLD-001","type":"dir_created","data":{"path":".codex/skills/team-code-review/","description":"Created skill directory structure"}}
{"ts":"2026-03-08T10:00:00Z","worker":"SCAFFOLD-001","type":"dir_created","data":{"path":"~ or <project>/.codex/skills/team-code-review/","description":"Created skill directory structure"}}
{"ts":"2026-03-08T10:05:00Z","worker":"ROLE-001","type":"file_generated","data":{"file":"roles/coordinator/role.md","gen_type":"role-bundle","sections":["entry-router","commands"]}}
{"ts":"2026-03-08T10:10:00Z","worker":"SPEC-001","type":"pattern_found","data":{"pattern_name":"full-lifecycle","description":"Pipeline with analyst -> writer -> executor -> tester"}}
```
@@ -651,3 +651,41 @@ All agents (csv-wave and interactive) share a single `discoveries.ndjson` file f
8. **Golden Sample Fidelity**: Generated files must match existing team skill patterns
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

6
.codex/skills/team-designer/schemas/tasks-schema.md
View File

@@ -78,8 +78,8 @@ Interactive tasks appear in master CSV for dependency tracking but are NOT inclu
```csv
id,title,description,role,file_target,gen_type,deps,context_from,exec_mode,wave,status,findings,files_produced,error
"SCAFFOLD-001","Create directory structure","Create complete directory structure for team-code-review skill:\n- .codex/skills/team-code-review/\n- roles/coordinator/ + commands/\n- roles/analyst/\n- roles/reviewer/\n- specs/\n- templates/","scaffolder","skill-dir","directory","","","csv-wave","1","pending","","",""
"ROUTER-001","Generate SKILL.md","Generate .codex/skills/team-code-review/SKILL.md with:\n- Frontmatter (name, description, allowed-tools)\n- Architecture diagram\n- Role registry table\n- CSV schema reference\n- Session structure\n- Wave execution engine\nUse teamConfig.json for role list and pipeline definitions","router-writer","SKILL.md","router","SCAFFOLD-001","SCAFFOLD-001","csv-wave","2","pending","","",""
"SCAFFOLD-001","Create directory structure","Create complete directory structure for team-code-review skill:\n- ~ or <project>/.codex/skills/team-code-review/\n- roles/coordinator/ + commands/\n- roles/analyst/\n- roles/reviewer/\n- specs/\n- templates/","scaffolder","skill-dir","directory","","","csv-wave","1","pending","","",""
"ROUTER-001","Generate SKILL.md","Generate ~ or <project>/.codex/skills/team-code-review/SKILL.md with:\n- Frontmatter (name, description, allowed-tools)\n- Architecture diagram\n- Role registry table\n- CSV schema reference\n- Session structure\n- Wave execution engine\nUse teamConfig.json for role list and pipeline definitions","router-writer","SKILL.md","router","SCAFFOLD-001","SCAFFOLD-001","csv-wave","2","pending","","",""
"SPEC-001","Generate pipelines spec","Generate specs/pipelines.md with:\n- Pipeline definitions from teamConfig\n- Task registry with PREFIX-NNN format\n- Conditional routing rules\n- Dynamic specialist injection\nRoles: analyst(ANALYSIS-*), reviewer(REVIEW-*)","spec-writer","specs/pipelines.md","spec","SCAFFOLD-001","SCAFFOLD-001","csv-wave","2","pending","","",""
"ROLE-001","Generate coordinator","Generate roles/coordinator/role.md with entry router and commands/analyze.md, commands/dispatch.md, commands/monitor.md. Coordinator orchestrates the analysis pipeline","role-writer","roles/coordinator/","role-bundle","SCAFFOLD-001;SPEC-001","SPEC-001","csv-wave","3","pending","","",""
"ROLE-002","Generate analyst role","Generate roles/analyst/role.md with Phase 2 (context loading), Phase 3 (analysis execution), Phase 4 (output). Prefix: ANALYSIS, inner_loop: false","role-writer","roles/analyst/role.md","role-inline","SCAFFOLD-001;SPEC-001","SPEC-001","csv-wave","3","pending","","",""
@@ -144,7 +144,7 @@ Interactive tasks output via structured text or JSON written to `interactive/{id
### Discovery NDJSON Format
```jsonl
{"ts":"2026-03-08T10:00:00Z","worker":"SCAFFOLD-001","type":"dir_created","data":{"path":".codex/skills/team-code-review/roles/","description":"Created roles directory with coordinator, analyst, reviewer subdirs"}}
{"ts":"2026-03-08T10:00:00Z","worker":"SCAFFOLD-001","type":"dir_created","data":{"path":"~ or <project>/.codex/skills/team-code-review/roles/","description":"Created roles directory with coordinator, analyst, reviewer subdirs"}}
{"ts":"2026-03-08T10:05:00Z","worker":"ROLE-001","type":"file_generated","data":{"file":"roles/coordinator/role.md","gen_type":"role-bundle","sections":["entry-router","phase-0","phase-1","phase-2","phase-3"]}}
{"ts":"2026-03-08T10:10:00Z","worker":"SPEC-001","type":"config_decision","data":{"decision":"full-lifecycle pipeline","rationale":"Both analyst and reviewer roles present","impact":"4-tier dependency graph"}}
```

67
.codex/skills/team-edict/SKILL.md
View File

@@ -217,8 +217,8 @@ Each wave generates a temporary `wave-{N}.csv` with extra `prev_context` column
4. Create subdirectories: plan/, review/, artifacts/, interactive/, agents/
5. Initialize registry.json: { "active": [], "closed": [] }
6. Initialize discoveries.ndjson (empty file)
7. Read specs: .codex/skills/team-edict/specs/team-config.json
8. Read quality gates: .codex/skills/team-edict/specs/quality-gates.md
7. Read specs: ~ or <project>/.codex/skills/team-edict/specs/team-config.json
8. Read quality gates: ~ or <project>/.codex/skills/team-edict/specs/quality-gates.md
9. Log session start to context.md
```
@@ -236,9 +236,9 @@ const zhongshu = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-edict/agents/zhongshu-planner.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-edict/agents/zhongshu-planner.md (MUST read first)
2. Read: ${sessionDir}/discoveries.ndjson (shared discoveries, skip if not exists)
3. Read: .codex/skills/team-edict/specs/team-config.json (routing rules)
3. Read: ~ or <project>/.codex/skills/team-edict/specs/team-config.json (routing rules)
---
@@ -285,7 +285,7 @@ while (!approved && reviewRound < 3) {
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-edict/agents/menxia-reviewer.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-edict/agents/menxia-reviewer.md (MUST read first)
2. Read: ${sessionDir}/plan/zhongshu-plan.md (plan to review)
3. Read: ${sessionDir}/discoveries.ndjson (shared discoveries)
@@ -336,10 +336,10 @@ const shangshu = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-edict/agents/shangshu-dispatcher.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-edict/agents/shangshu-dispatcher.md (MUST read first)
2. Read: ${sessionDir}/plan/zhongshu-plan.md (approved plan)
3. Read: ${sessionDir}/review/menxia-review.md (review conditions)
4. Read: .codex/skills/team-edict/specs/team-config.json (routing rules)
4. Read: ~ or <project>/.codex/skills/team-edict/specs/team-config.json (routing rules)
---
@@ -416,8 +416,8 @@ For each wave W in 1..max_wave:
5. EXECUTE csv-wave tasks:
spawn_agents_on_csv({
task_csv_path: "${sessionDir}/wave-{W}.csv",
instruction_path: ".codex/skills/team-edict/instructions/agent-instruction.md",
schema_path: ".codex/skills/team-edict/schemas/tasks-schema.md",
instruction_path: "~ or <project>/.codex/skills/team-edict/instructions/agent-instruction.md",
schema_path: "~ or <project>/.codex/skills/team-edict/schemas/tasks-schema.md",
additional_instructions: "Session directory: ${sessionDir}. Department: {department}. Priority: {priority}.",
concurrency: CONCURRENCY
})
@@ -457,10 +457,10 @@ const aggregator = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-edict/agents/aggregator.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-edict/agents/aggregator.md (MUST read first)
2. Read: ${sessionDir}/tasks.csv (master state)
3. Read: ${sessionDir}/discoveries.ndjson (all discoveries)
4. Read: .codex/skills/team-edict/specs/quality-gates.md (quality standards)
4. Read: ~ or <project>/.codex/skills/team-edict/specs/quality-gates.md (quality standards)
---
@@ -472,7 +472,7 @@ Deliverables: ${sessionDir}/context.md (final report)
${listAllArtifacts()}
### Quality Gate Standards
Read from: .codex/skills/team-edict/specs/quality-gates.md
Read from: ~ or <project>/.codex/skills/team-edict/specs/quality-gates.md
`
})
@@ -609,9 +609,9 @@ const agent = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-edict/agents/qa-verifier.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-edict/agents/qa-verifier.md (MUST read first)
2. Read: ${sessionDir}/discoveries.ndjson (shared discoveries)
3. Read: .codex/skills/team-edict/specs/quality-gates.md (quality standards)
3. Read: ~ or <project>/.codex/skills/team-edict/specs/quality-gates.md (quality standards)
---
@@ -740,3 +740,42 @@ spawn_agent({
12. **Rejection Loop Max 3**: Menxia can reject max 3 times before escalating to user
13. **Kanban is Mandatory**: All agents must report state transitions via discoveries.ndjson
14. **Quality Gates Apply**: Phase 3 aggregator validates all outputs against specs/quality-gates.md
---
## Coordinator Role Constraints (Crown Prince / Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned agents (Three Departments and Six Ministries). The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results into master CSV
- Coordinates workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms (600s for planning, 300s for execution)
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages (e.g., jumping from Zhongshu directly to Shangshu)
- Bypass the Three Departments serial pipeline
- Execute wave N before wave N-1 completes
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time: 30-90 minutes for typical edicts
- Phase 0 (Three Departments): 15-30 minutes
- Phase 2 (Wave Execution): 10-20 minutes per wave
- Phase 3 (Aggregation): 5-10 minutes
- The coordinator must remain active and attentive throughout the entire process

2
.codex/skills/team-edict/agents/aggregator.md
View File

@@ -68,7 +68,7 @@ Post-wave aggregation agent -- collects all ministry outputs, validates against
4. Use Glob to find all files in `<session>/interactive/`
5. Read each interactive result file
6. Read `<session>/discoveries.ndjson` (all entries)
7. Read `.codex/skills/team-edict/specs/quality-gates.md`
7. Read `~ or <project>/.codex/skills/team-edict/specs/quality-gates.md`
**Output**: All artifacts and status data collected

2
.codex/skills/team-edict/agents/qa-verifier.md
View File

@@ -64,7 +64,7 @@ Xingbu (Ministry of Justice / Quality Assurance) -- executes quality verificatio
**Steps**:
1. Read `.codex/skills/team-edict/specs/quality-gates.md`
1. Read `~ or <project>/.codex/skills/team-edict/specs/quality-gates.md`
2. Read `<session>/plan/dispatch-plan.md` for acceptance criteria
3. Read implementation artifacts from `<session>/artifacts/`
4. Read `<session>/discoveries.ndjson` for implementation notes

2
.codex/skills/team-edict/agents/shangshu-dispatcher.md
View File

@@ -62,7 +62,7 @@ Shangshu (Department of State Affairs / Dispatch) -- parses the approved plan, r
1. Read `<session>/plan/zhongshu-plan.md`
2. Read `<session>/review/menxia-review.md`
3. Read `.codex/skills/team-edict/specs/team-config.json`
3. Read `~ or <project>/.codex/skills/team-edict/specs/team-config.json`
4. Extract subtask list from plan
5. Extract conditions from review
6. Report state "Doing":

2
.codex/skills/team-edict/agents/zhongshu-planner.md
View File

@@ -64,7 +64,7 @@ Zhongshu (Central Secretariat) -- analyzes the edict, explores the codebase, and
**Steps**:
1. Parse the edict text from the spawn message
2. Read `.codex/skills/team-edict/specs/team-config.json` for routing rules
2. Read `~ or <project>/.codex/skills/team-edict/specs/team-config.json` for routing rules
3. If revision round: Read `<session>/review/menxia-review.md` for rejection feedback
4. Read `<session>/discoveries.ndjson` if it exists

4
.codex/skills/team-edict/instructions/agent-instruction.md
View File

@@ -4,8 +4,8 @@
1. Read shared discoveries: .workflow/.csv-wave/{session-id}/discoveries.ndjson (if exists, skip if not)
2. Read dispatch plan: .workflow/.csv-wave/{session-id}/plan/dispatch-plan.md (task details and acceptance criteria)
3. Read approved plan: .workflow/.csv-wave/{session-id}/plan/zhongshu-plan.md (overall strategy and context)
4. Read quality gates: .codex/skills/team-edict/specs/quality-gates.md (quality standards)
5. Read team config: .codex/skills/team-edict/specs/team-config.json (routing rules and artifact paths)
4. Read quality gates: ~ or <project>/.codex/skills/team-edict/specs/quality-gates.md (quality standards)
5. Read team config: ~ or <project>/.codex/skills/team-edict/specs/team-config.json (routing rules and artifact paths)
> **Note**: The session directory path is provided by the orchestrator in `additional_instructions`. Use it to resolve the paths above.

38
.codex/skills/team-executor/SKILL.md
View File

@@ -475,3 +475,41 @@ if (action === "Archive & Clean") {
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent (tracked in registry.json)
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-frontend-debug/SKILL.md
View File

@@ -781,3 +781,41 @@ After TEST-001 completes, evaluate issues:
9. **Iteration Bounds**: Max 2 reproduction rounds, max 3 fix rounds
10. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
11. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-frontend/SKILL.md
View File

@@ -710,3 +710,41 @@ Convergence: qa.score >= 8 && qa.critical_count === 0
8. **GC Loop Cap**: Max 2 generator-critic rounds between developer and qa
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

44
.codex/skills/team-issue/SKILL.md
View File

@@ -389,7 +389,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
spawn_agents_on_csv({
csv_path: `${sessionFolder}/wave-${wave}.csv`,
id_column: "id",
instruction: Read(".codex/skills/team-issue/instructions/agent-instruction.md"),
instruction: Read("~ or <project>/.codex/skills/team-issue/instructions/agent-instruction.md"),
max_concurrency: maxConcurrency,
max_runtime_seconds: 1200,
output_csv_path: `${sessionFolder}/wave-${wave}-results.csv`,
@@ -420,7 +420,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
const pendingInteractive = interactiveTasks.filter(t => t.status === 'pending')
for (const task of pendingInteractive) {
// Read agent definition
const agentDef = Read(`.codex/skills/team-issue/agents/reviewer.md`)
const agentDef = Read(`~ or <project>/.codex/skills/team-issue/agents/reviewer.md`)
// Build context from upstream tasks
const contextIds = (task.context_from || '').split(';').filter(Boolean)
@@ -434,7 +434,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
message: `## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-issue/agents/reviewer.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-issue/agents/reviewer.md (MUST read first)
2. Read: ${sessionFolder}/discoveries.ndjson (shared discoveries)
3. Read: .workflow/project-tech.json (if exists)
@@ -700,3 +700,41 @@ Both csv-wave and interactive agents share the same discoveries.ndjson file:
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

44
.codex/skills/team-iterdev/SKILL.md
View File

@@ -290,7 +290,7 @@ const analyzer = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-iterdev/agents/task-analyzer.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-iterdev/agents/task-analyzer.md (MUST read first)
2. Read: .workflow/project-tech.json (if exists)
---
@@ -484,7 +484,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
const waveResult = spawn_agents_on_csv({
csv_path: `${sessionFolder}/wave-${wave}.csv`,
id_column: "id",
instruction: Read(`.codex/skills/team-iterdev/instructions/agent-instruction.md`),
instruction: Read(`~ or <project>/.codex/skills/team-iterdev/instructions/agent-instruction.md`),
max_concurrency: maxConcurrency,
max_runtime_seconds: 900,
output_csv_path: `${sessionFolder}/wave-${wave}-results.csv`,
@@ -533,7 +533,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-iterdev/agents/gc-controller.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-iterdev/agents/gc-controller.md (MUST read first)
2. Read: ${sessionFolder}/discoveries.ndjson (shared discoveries)
---
@@ -786,3 +786,41 @@ When the reviewer returns review results with severity-graded verdicts:
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

44
.codex/skills/team-lifecycle-v4/SKILL.md
View File

@@ -254,7 +254,7 @@ const clarifier = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-lifecycle-v4/agents/requirement-clarifier.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-lifecycle-v4/agents/requirement-clarifier.md (MUST read first)
2. Read: .workflow/project-tech.json (if exists)
---
@@ -436,7 +436,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
const waveResult = spawn_agents_on_csv({
csv_path: `${sessionFolder}/wave-${wave}.csv`,
id_column: "id",
instruction: Read(`.codex/skills/team-lifecycle-v4/instructions/agent-instruction.md`)
instruction: Read(`~ or <project>/.codex/skills/team-lifecycle-v4/instructions/agent-instruction.md`)
.replace(/{session-id}/g, sessionId),
max_concurrency: maxConcurrency,
max_runtime_seconds: 900,
@@ -486,7 +486,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-lifecycle-v4/agents/supervisor.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-lifecycle-v4/agents/supervisor.md (MUST read first)
2. Read: ${sessionFolder}/discoveries.ndjson (shared discoveries)
---
@@ -735,3 +735,41 @@ All agents across all waves share `discoveries.ndjson`. This enables cross-role
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-lifecycle/SKILL.md
View File

@@ -866,3 +866,41 @@ The orchestrator dynamically adds DEV-FE-NNN and QA-FE-NNN tasks to the state fi
| Requirements Template | templates/requirements-prd.md | DRAFT-002 |
| Architecture Template | templates/architecture-doc.md | DRAFT-003 |
| Epics Template | templates/epics-template.md | DRAFT-004 |
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

12
.codex/skills/team-lifecycle/agents/analyst.md
View File

@@ -5,7 +5,7 @@ Seed analysis, codebase exploration (via shared explore subagent), and multi-dim
## Identity
- **Type**: `produce`
- **Role File**: `~/.codex/skills/team-lifecycle/agents/analyst.md`
- **Role File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/analyst.md`
- **Prefix**: `RESEARCH-*`
- **Tag**: `[analyst]`
- **Responsibility**: Seed Analysis -> Codebase Exploration -> Context Packaging -> Inline Discuss -> Report
@@ -168,7 +168,7 @@ if (cached) {
// Cache MISS - spawn explore subagent
const explorer = spawn_agent({
message: `### MANDATORY FIRST STEPS
1. Read: ~/.codex/skills/team-lifecycle/agents/explore-agent.md
1. Read: ~/~ or <project>/.codex/skills/team-lifecycle/agents/explore-agent.md
---
@@ -253,7 +253,7 @@ After packaging, spawn discuss subagent (Pattern 2.8):
```javascript
const critic = spawn_agent({
message: `### MANDATORY FIRST STEPS
1. Read: ~/.codex/skills/team-lifecycle/agents/discuss-agent.md
1. Read: ~/~ or <project>/.codex/skills/team-lifecycle/agents/discuss-agent.md
## Multi-Perspective Critique: DISCUSS-001
@@ -297,7 +297,7 @@ This agent spawns two utility subagents during its execution:
### Explore Subagent (Phase 3)
**When**: After seed analysis, when project files detected
**Agent File**: `~/.codex/skills/team-lifecycle/agents/explore-agent.md`
**Agent File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/explore-agent.md`
**Pattern**: 2.9 (Cache-Aware Exploration)
See Phase 3 code block above. Cache is checked before spawning. If cache hit, the spawn is skipped entirely.
@@ -305,7 +305,7 @@ See Phase 3 code block above. Cache is checked before spawning. If cache hit, th
### Discuss Subagent (Phase 4b)
**When**: After context packaging (spec-config.json + discovery-context.json written)
**Agent File**: `~/.codex/skills/team-lifecycle/agents/discuss-agent.md`
**Agent File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/discuss-agent.md`
**Pattern**: 2.8 (Inline Subagent)
See Phase 4b code block above.
@@ -342,7 +342,7 @@ if (cached) {
// Cache MISS - spawn explore subagent, result cached by explore-agent
const explorer = spawn_agent({
message: `### MANDATORY FIRST STEPS
1. Read: ~/.codex/skills/team-lifecycle/agents/explore-agent.md
1. Read: ~/~ or <project>/.codex/skills/team-lifecycle/agents/explore-agent.md
---

2
.codex/skills/team-lifecycle/agents/discuss-agent.md
View File

@@ -5,7 +5,7 @@ Lightweight multi-perspective critique engine. Called inline by produce agents (
## Identity
- **Type**: `utility`
- **Role File**: `~/.codex/skills/team-lifecycle/agents/discuss-agent.md`
- **Role File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/discuss-agent.md`
- **Tag**: `[discuss]`
- **Responsibility**: Read Artifact -> Multi-CLI Perspective Analysis -> Divergence Detection -> Consensus Determination -> Write Discussion Record -> Return Verdict

6
.codex/skills/team-lifecycle/agents/explore-agent.md
View File

@@ -5,7 +5,7 @@ Shared codebase exploration utility with centralized caching. Callable by any ag
## Identity
- **Type**: `utility`
- **Role File**: `~/.codex/skills/team-lifecycle/agents/explore-agent.md`
- **Role File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/explore-agent.md`
- **Tag**: `[explore]`
- **Responsibility**: Cache Check -> Codebase Exploration -> Cache Update -> Return Structured Results
@@ -382,7 +382,7 @@ if (cached && !forceRefresh) {
// After seed analysis, explore codebase context (Pattern 2.9 in analyst)
const explorer = spawn_agent({
message: `### MANDATORY FIRST STEPS
1. Read: ~/.codex/skills/team-lifecycle/agents/explore-agent.md
1. Read: ~/~ or <project>/.codex/skills/team-lifecycle/agents/explore-agent.md
---
@@ -405,7 +405,7 @@ for (const angle of angles) {
// Cache check happens inside explore-agent
const explorer = spawn_agent({
message: `### MANDATORY FIRST STEPS
1. Read: ~/.codex/skills/team-lifecycle/agents/explore-agent.md
1. Read: ~/~ or <project>/.codex/skills/team-lifecycle/agents/explore-agent.md
---

6
.codex/skills/team-lifecycle/agents/writer.md
View File

@@ -5,7 +5,7 @@ Product Brief, Requirements/PRD, Architecture, and Epics & Stories document gene
## Identity
- **Type**: `produce`
- **Role File**: `~/.codex/skills/team-lifecycle/agents/writer.md`
- **Role File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/writer.md`
- **Prefix**: `DRAFT-*`
- **Tag**: `[writer]`
- **Responsibility**: Load Context -> Generate Document -> Self-Validation -> Inline Discuss -> Report
@@ -382,7 +382,7 @@ After validation, spawn discuss subagent (Pattern 2.8) for this task's discuss r
```javascript
const critic = spawn_agent({
message: `### MANDATORY FIRST STEPS
1. Read: ~/.codex/skills/team-lifecycle/agents/discuss-agent.md
1. Read: ~/~ or <project>/.codex/skills/team-lifecycle/agents/discuss-agent.md
## Multi-Perspective Critique: <DISCUSS-NNN>
@@ -435,7 +435,7 @@ This agent spawns the discuss subagent during Phase 4b:
### Discuss Subagent (Phase 4b)
**When**: After self-validation of generated document
**Agent File**: `~/.codex/skills/team-lifecycle/agents/discuss-agent.md`
**Agent File**: `~/~ or <project>/.codex/skills/team-lifecycle/agents/discuss-agent.md`
**Pattern**: 2.8 (Inline Subagent)
See Phase 4b code block above. The round ID and perspectives vary per doc type -- use the Inline Discuss Mapping table.

2
.codex/skills/team-lifecycle/phases/01-requirement-clarification.md
View File

@@ -1,6 +1,6 @@
# Phase 1: Requirement Clarification
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/.codex/skills/team-lifecycle/phases/01-requirement-clarification.md")` before continuing. Never execute based on summaries.
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/~ or <project>/.codex/skills/team-lifecycle/phases/01-requirement-clarification.md")` before continuing. Never execute based on summaries.
## Objective

2
.codex/skills/team-lifecycle/phases/02-team-initialization.md
View File

@@ -1,6 +1,6 @@
# Phase 2: Team Initialization
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/.codex/skills/team-lifecycle/phases/02-team-initialization.md")` before continuing. Never execute based on summaries.
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/~ or <project>/.codex/skills/team-lifecycle/phases/02-team-initialization.md")` before continuing. Never execute based on summaries.
## Objective

2
.codex/skills/team-lifecycle/phases/03-task-chain-creation.md
View File

@@ -1,6 +1,6 @@
# Phase 3: Task Chain Creation
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/.codex/skills/team-lifecycle/phases/03-task-chain-creation.md")` before continuing. Never execute based on summaries.
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/~ or <project>/.codex/skills/team-lifecycle/phases/03-task-chain-creation.md")` before continuing. Never execute based on summaries.
## Objective

2
.codex/skills/team-lifecycle/phases/04-pipeline-coordination.md
View File

@@ -1,6 +1,6 @@
# Phase 4: Pipeline Coordination
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/.codex/skills/team-lifecycle/phases/04-pipeline-coordination.md")` before continuing. Never execute based on summaries.
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/~ or <project>/.codex/skills/team-lifecycle/phases/04-pipeline-coordination.md")` before continuing. Never execute based on summaries.
## Objective

2
.codex/skills/team-lifecycle/phases/05-completion-report.md
View File

@@ -1,6 +1,6 @@
# Phase 5: Completion Report
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/.codex/skills/team-lifecycle/phases/05-completion-report.md")` before continuing. Never execute based on summaries.
> **COMPACT PROTECTION**: This is an execution document. After context compression, phase instructions become summaries only. You MUST immediately re-read this file via `Read("~/~ or <project>/.codex/skills/team-lifecycle/phases/05-completion-report.md")` before continuing. Never execute based on summaries.
## Objective

38
.codex/skills/team-perf-opt/SKILL.md
View File

@@ -657,3 +657,41 @@ All agents (csv-wave and interactive) share a single `discoveries.ndjson` file f
8. **Max 3 Fix Cycles**: Review-fix cycle capped at 3 iterations; escalate to user after
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

2
.codex/skills/team-perf-opt/instructions/agent-instruction.md
View File

@@ -3,7 +3,7 @@
### MANDATORY FIRST STEPS
1. Read shared discoveries: {session_folder}/discoveries.ndjson (if exists, skip if not)
2. Read project context: .workflow/project-tech.json (if exists)
3. Read task schema: .codex/skills/team-perf-opt/schemas/tasks-schema.md
3. Read task schema: ~ or <project>/.codex/skills/team-perf-opt/schemas/tasks-schema.md
---

40
.codex/skills/team-planex-v2/SKILL.md
View File

@@ -429,7 +429,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
spawn_agents_on_csv({
csv_path: `${sessionFolder}/wave-${wave}.csv`,
id_column: "id",
instruction: Read(".codex/skills/team-planex/instructions/agent-instruction.md"),
instruction: Read("~ or <project>/.codex/skills/team-planex/instructions/agent-instruction.md"),
max_concurrency: maxConcurrency,
max_runtime_seconds: 1200,
output_csv_path: `${sessionFolder}/wave-${wave}-results.csv`,
@@ -597,3 +597,41 @@ Both planner and executor agents share the same discoveries.ndjson file:
8. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
9. **Two-Wave Pipeline**: Wave 1 = Planning (PLAN-*), Wave 2 = Execution (EXEC-*)
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-planex/SKILL.md
View File

@@ -501,3 +501,41 @@ if (plannerAgent) {
|---------|--------|
| `check` / `status` | Show progress: planned / executing / completed / failed counts |
| `resume` / `continue` | Re-enter loop from Phase 2 |
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-quality-assurance/SKILL.md
View File

@@ -774,3 +774,41 @@ QAGEN -> QARUN -> (if coverage < target) -> GC Loop Handler
9. **Scout Feeds Strategy**: Scout findings flow into strategist via prev_context and discoveries.ndjson
10. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
11. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-review/SKILL.md
View File

@@ -493,3 +493,41 @@ send_input({
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent (tracked in registry.json)
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-roadmap-dev/SKILL.md
View File

@@ -643,3 +643,41 @@ const discoveries = Read(`${sessionDir}/discoveries.ndjson`)
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent (tracked in registry.json)
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-tech-debt/SKILL.md
View File

@@ -668,3 +668,41 @@ Wave 3: TDVAL-001 (validator) -> 4-layer validation
8. **GC Loop Bounded**: Maximum 3 fix-verify rounds before accepting current state
9. **Worktree Isolation**: All fix execution happens in git worktree, not main branch
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-testing/SKILL.md
View File

@@ -730,3 +730,41 @@ TESTGEN -> TESTRUN -> (if pass_rate < 0.95 OR coverage < target) -> GC Loop Hand
8. **GC Loop Discipline**: Max 3 rounds per layer; never infinite-loop on coverage
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-uidesign/SKILL.md
View File

@@ -727,3 +727,41 @@ Convergence: audit.score >= 8 AND audit.critical_count === 0
8. **GC Loop Cap**: Max 2 generator-critic rounds between designer and reviewer
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

42
.codex/skills/team-ultra-analyze/SKILL.md
View File

@@ -237,7 +237,7 @@ const analyzer = spawn_agent({
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-ultra-analyze/agents/topic-analyzer.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-ultra-analyze/agents/topic-analyzer.md (MUST read first)
2. Read: .workflow/project-tech.json (if exists)
---
@@ -497,7 +497,7 @@ for (let wave = 1; wave <= maxWave; wave++) {
## TASK ASSIGNMENT
### MANDATORY FIRST STEPS (Agent Execute)
1. **Read role definition**: .codex/skills/team-ultra-analyze/agents/discussion-feedback.md (MUST read first)
1. **Read role definition**: ~ or <project>/.codex/skills/team-ultra-analyze/agents/discussion-feedback.md (MUST read first)
2. Read: ${sessionFolder}/discoveries.ndjson (shared discoveries)
---
@@ -747,3 +747,41 @@ All agents across all waves share `discoveries.ndjson`. This enables cross-role
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns

38
.codex/skills/team-ux-improve/SKILL.md
View File

@@ -599,3 +599,41 @@ All agents share `discoveries.ndjson` for UX findings.
8. **Lifecycle Balance**: Every spawn_agent has matching close_agent
9. **Cleanup Temp Files**: Remove wave-{N}.csv after merge
10. **DO NOT STOP**: Continuous execution until all waves complete
---
## Coordinator Role Constraints (Main Agent)
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
- Spawns agents with task assignments
- Waits for agent callbacks
- Merges results and coordinates workflow
- Manages workflow transitions between phases
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
- Wait patiently for `wait()` calls to complete
- NOT skip workflow steps due to perceived delays
- NOT assume agents have failed just because they're taking time
- Trust the timeout mechanisms defined in the skill
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
- Use `send_input()` to ask questions or provide clarification
- NOT skip the agent or move to next phase prematurely
- Give agents opportunity to respond before escalating
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
- Skip phases or stages defined in the workflow
- Bypass required approval or review steps
- Execute dependent tasks before prerequisites complete
- Assume task completion without explicit agent callback
- Make up or fabricate agent results
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
- Total execution time may range from 30-90 minutes or longer
- Each phase may take 10-30 minutes depending on complexity
- The coordinator must remain active and attentive throughout the entire process
- Do not terminate or skip steps due to time concerns