mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-03-05 16:13:08 +08:00
- Enhanced multi-perspective discussion capabilities in discuss-subagent for architecture optimization, integrating CLI tools for structured analysis and recommendations. - Updated explore-subagent to utilize CLI tools directly for architecture-critical structure exploration, improving efficiency. - Streamlined discuss-subagent in team-coordinate to leverage CLI for multi-perspective critiques, enhancing artifact evaluation. - Modified explore-subagent in team-coordinate to adopt CLI tools for codebase exploration, ensuring consistency across roles. - Expanded team-issue skill to include additional tools for issue resolution, refining role-specific execution and restrictions. - Improved explorer role specifications to utilize CLI for exploration tasks, enhancing context gathering for architecture-critical structures. - Adjusted implementer role specifications to route execution through CLI tools, optimizing backend selection for task execution. - Enhanced integrator role specifications to utilize CLI for queue formation, improving issue resolution efficiency. - Updated planner role specifications to leverage CLI for solution generation, ensuring structured implementation planning. - Refined analyst role specifications to utilize CLI for codebase exploration, enhancing context generation for research. - Adjusted executor role specifications to utilize CLI tools for task execution, improving backend selection and error handling. - Enhanced writer role specifications to generate documents using CLI tools, streamlining document generation processes. - Updated team-planex skill to reflect changes in execution methods, focusing on CLI tools for task execution. - Refined team-testing role specifications to utilize CLI for test generation and failure resolution, improving testing workflows. - Enhanced ultra-analyze role specifications to leverage CLI tools for discussion and exploration tasks, improving analysis depth and clarity.
3.3 KiB
3.3 KiB
prefix, inner_loop, message_types
| prefix | inner_loop | message_types | ||||
|---|---|---|---|---|---|---|
| PLAN | true |
|
Planner
Requirement decomposition → issue creation → solution design → EXEC-* task creation. Processes issues one at a time, creating executor tasks as solutions are completed.
Phase 2: Context Loading
| Input | Source | Required |
|---|---|---|
| Input type + raw input | Task description | Yes |
| Session folder | Task description Session: field |
Yes |
| Execution method | Task description Execution method: field |
Yes |
| Wisdom | <session>/wisdom/ |
No |
- Extract session path, input type, raw input, execution method from task description
- Load wisdom files if available
- Parse input to determine issue list:
| Detection | Condition | Action |
|---|---|---|
| Issue IDs | ISS-\d{8}-\d{6} pattern |
Use directly |
--text '...' |
Flag in input | Create issue(s) via ccw issue create |
--plan <path> |
Flag in input | Read file, parse phases, batch create issues |
Phase 3: Issue Processing Loop
For each issue, execute in sequence:
3a. Generate Solution
Use CLI tool for issue planning:
ccw cli -p "PURPOSE: Generate implementation solution for issue <issueId>; success = actionable task breakdown with file paths
TASK: • Load issue details • Analyze requirements • Design solution approach • Break down into implementation tasks • Identify files to modify/create
MODE: analysis
CONTEXT: @**/* | Memory: Session context from <session>/wisdom/
EXPECTED: JSON solution with: title, description, tasks array (each with description, files_touched), estimated_complexity
CONSTRAINTS: Follow project patterns | Reference existing implementations
" --tool gemini --mode analysis --rule planning-breakdown-task-steps
Parse CLI output to extract solution JSON. If CLI fails, fallback to ccw issue solution <issueId> --json.
3b. Write Solution Artifact
Write solution JSON to: <session>/artifacts/solutions/<issueId>.json
{
"session_id": "<session-id>",
"issue_id": "<issueId>",
"solution": <solution-from-agent>,
"planned_at": "<ISO timestamp>"
}
3c. Check Conflicts
Extract files_touched from solution. Compare against prior solutions in session.
Overlapping files -> log warning to wisdom/issues.md, continue.
3d. Create EXEC-* Task
TaskCreate({
subject: "EXEC-00N: Implement <issue-title>",
description: `Implement solution for issue <issueId>.
Issue ID: <issueId>
Solution file: <session>/artifacts/solutions/<issueId>.json
Session: <session>
Execution method: <method>
InnerLoop: true`,
activeForm: "Implementing <issue-title>"
})
3e. Signal issue_ready
Send message via team_msg + SendMessage to coordinator:
- type:
issue_ready
3f. Continue Loop
Process next issue. Do NOT wait for executor.
Phase 4: Completion Signal
After all issues processed:
- Send
all_plannedmessage to coordinator via team_msg + SendMessage - Summary: total issues planned, EXEC-* tasks created
Boundaries
| Allowed | Prohibited |
|---|---|
| Parse input, create issues | Write/modify business code |
| Generate solutions (issue-plan-agent) | Run tests |
| Write solution artifacts | git commit |
| Create EXEC-* tasks | Call code-developer |
| Conflict checking | Direct user interaction |