catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-05 01:50:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: Remove redundant schema details, let planning agent read schema independently

Browse Source 
- Remove detailed plan.json structure from prompt (agent reads schema file)
- Clarify execution steps: agent reads schema first, then explores and generates
- Remove ambiguous "Execute CLI planning using Gemini" step

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-12-17 23:36:41 +08:00
parent 6aac7bb8e3
commit 79da2c8c17
1 changed files with 8 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
.claude/commands/workflow/lite-plan.md
View File

@@ -417,23 +417,9 @@ ${JSON.stringify(clarificationContext) || "None"}
${complexity} ${complexity}
## Requirements ## Requirements
Generate plan.json with: Generate plan.json following the schema obtained above. Key constraints:
- summary: 2-3 sentence overview - tasks: 2-7 structured tasks (**group by feature/module, NOT by file**)
- approach: High-level implementation strategy (incorporating insights from all exploration angles) - _metadata.exploration_angles: ${JSON.stringify(manifest.explorations.map(e => e.angle))}
- tasks: 2-7 structured tasks (**IMPORTANT: group by feature/module, NOT by file**)
- **Task Granularity Principle**: Each task = one complete feature unit or module
- title: action verb + target module/feature (e.g., "Implement auth token refresh")
- scope: module path (src/auth/) or feature name, prefer module-level over single file
- action, description
- modification_points: ALL files to modify for this feature (group related changes)
- implementation (3-7 steps covering all modification_points)
- reference (pattern, files, examples)
- acceptance (2-4 criteria for the entire feature)
- depends_on: task IDs this task depends on (use sparingly, only for true dependencies)
- estimated_time, recommended_execution, complexity
- _metadata:
- timestamp, source, planning_mode
- exploration_angles: ${JSON.stringify(manifest.explorations.map(e => e.angle))}
## Task Grouping Rules ## Task Grouping Rules
1. **Group by feature**: All changes for one feature = one task (even if 3-5 files) 1. **Group by feature**: All changes for one feature = one task (even if 3-5 files)
@@ -445,12 +431,11 @@ Generate plan.json with:
7. **Prefer parallel**: Most tasks should be independent (no depends_on) 7. **Prefer parallel**: Most tasks should be independent (no depends_on)
## Execution ## Execution
1. Read ALL exploration files for comprehensive context 1. Read schema file (cat command above)
2. Execute CLI planning using Gemini (Qwen fallback) 2. Read ALL exploration files for comprehensive context
3. Synthesize findings from multiple exploration angles 3. Synthesize findings and generate plan following schema
4. Parse output and structure plan 4. Write JSON: Write('${sessionFolder}/plan.json', jsonContent)
5. Write JSON: Write('${sessionFolder}/plan.json', jsonContent) 5. Return brief completion summary
6. Return brief completion summary
` `
) )
``` ```