catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-13 02:41:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove granular progress tracking across workflow system

Browse Source 
- Remove detailed progress views (Total Tasks: X, Completed: Y %) from all templates
- Simplify TODO_LIST.md structure by removing Progress Overview sections
- Remove stats tracking from session-management-principles.json schema
- Eliminate progress format and calculation logic from context command
- Remove percentage-based progress displays from action-planning-agent
- Simplify vibe command coordination by removing detailed task counts
- Focus on essential JSON state changes rather than UI progress metrics

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-09-08 15:26:01 +08:00
parent da717546f8
commit 9502741d50
17 changed files with 2064 additions and 3449 deletions
Download Patch File Download Diff File Expand all files Collapse all files

120
.claude/output-styles/agent-workflow-coordination.md
View File

@@ -1,13 +1,7 @@
---
name: Agent Workflow Coordination
name: Workflow Coordination
description: Core coordination principles for multi-agent development workflows
---
## System Reference
**Complete Architecture**: @~/.claude/workflows/core-principles.md
This document defines essential coordination principles between agents. For complete system architecture, file structures, commands, and implementation details, refer to the unified workflow system principles.
## Core Agent Coordination Principles
### Planning First Principle
@@ -36,101 +30,27 @@ This document defines essential coordination principles between agents. For comp
6. **Checkpoint Safety**: State is saved automatically after each agent completes its work.
7. **Interrupt/Resume**: The system must support full state preservation and restoration.
### Implementation Prerequisites Principle
## Context Management
**Deliverable Validation**: Code modification agents can only execute when proper planning deliverables exist.
### Gemini Context Protocol
**Context Integration**: Agents use Gemini CLI for context gathering when needed, with memory-gemini-bridge agent handling complex analysis.
**Required Artifacts Before Implementation** (at least one must exist):
- `IMPL_PLAN.md`: Must contain detailed implementation strategy
- `.chat/` sessions: Context analysis supporting planning decisions
- Task definitions: JSON task files with clear acceptance criteria
- Complexity assessment: Validated task complexity and scope
**CLI Guidelines Reference**: Follow @~/.cluade/workflows/gemini-cli-guidelines.md for consistency and `memory-gemini-bridge` agent for comprehensive analysis.
**Validation Protocol**:
```pseudo
FUNCTION validate_implementation_prerequisites():
artifacts_found = 0
IF exists("IMPL_PLAN.md") AND valid_content("IMPL_PLAN.md"):
artifacts_found += 1
IF exists(".chat/") AND NOT empty_directory(".chat/"):
artifacts_found += 1
IF validate_task_definitions():
artifacts_found += 1
IF has_complexity_assessment():
artifacts_found += 1
IF artifacts_found == 0:
BLOCK_IMPLEMENTATION("No planning artifacts found - at least one required")
IF artifacts_found < 2:
WARN_IMPLEMENTATION("Limited planning context - recommend additional artifacts")
RETURN READY_FOR_IMPLEMENTATION
END FUNCTION
```
### 🎯 Gemini CLI Requirements by Task Complexity
### Core Workflow Process
#### 🚀 Simple Tasks (CLI Optional)
**Task Examples**: Single file modifications, documentation updates, text changes, simple bug fixes
**CLI Decision**: Optional - only when unfamiliar patterns encountered
**Context Scope**: Basic guidelines and patterns
`TodoWrite Creation` **->** `Context Collection` **->** `Implementation` **->** `Quality Assurance` **->** `State Update`
### Interrupt & Resume Protocol
**Checkpoint Strategy Flow:**
`Agent Completes` **->** `Save State (Todo + Context)` **->** `Check for Interrupt Signal` **->** `Continue or Stop`
**State Components for Resume**:
- TodoWrite current state
- Agent output chain
- Accumulated context
- Planning documents
- `.chat/` analysis history
### Agent Selection Logic
```pseudo
FUNCTION select_agent_for_task(task_complexity):
CASE task_complexity:
WHEN 'Research/Analysis':
RETURN "General-Purpose" // For research, file analysis
WHEN 'Simple Implementation':
RETURN "Code Developer" // For implementation, TDD, algorithms
WHEN 'Complex Features (3+ components)':
RETURN ["Action Planning", "Code Developer", "Code Review"] // Multi-stage agent chain
WHEN 'Full Lifecycle':
RETURN "Boomerang" // For full workflow orchestration
WHEN 'Post-Implementation':
RETURN "Code Review" // For quality validation, security, compliance
END FUNCTION
```
### Agent Output Standards
**Action Planning Agent**:
```
PLAN_SUMMARY: [One-line summary]
STEPS: [Numbered deliverables]
SUCCESS_CRITERIA: [Measurable standards]
TODOWRITE_ENTRIES: [TodoWrite items created for each stage/subtask]
```
**Code Developer Agent**:
```
PREREQUISITE_VALIDATION: [IMPL_PLAN.md and .chat/ sessions verified]
IMPLEMENTATION_SUMMARY: [What was built]
FILES_MODIFIED: [File list with changes]
CONTEXT_REFERENCES: [Links to supporting .chat/ analysis]
TODOWRITE_UPDATES: [Progress status updates made during implementation]
READY_FOR_REVIEW: [YES/NO with reason]
```
**Code Review Agent**:
```
REVIEW_STATUS: [PASS/ISSUES_FOUND/CRITICAL_ISSUES]
QUALITY_SCORE: [1-10]
TODOWRITE_COMPLETION: [Tasks marked as completed after validation]
RECOMMENDATION: [APPROVE/FIX_REQUIRED/REVISION_NEEDED]
```
#### 🎯 Medium Tasks (CLI Recommended)
**Task Examples**: Multi-file features, component modifications, API endpoint additions
**CLI Decision**: Recommended for consistency and quality
**Context Scope**: Guidelines + architecture + feature patterns
**Standard Context Collection**:
```bash
gemini --all-files -p "@{**/*CLAUDE.md} Guidelines for: [task]"
gemini --all-files -p "@[modules] Architecture for: [task]"
gemini --all-files -p "@[files] Patterns for: [task]"
```