lmiranda
0e70156e26
Separate cognitive work from mechanical API execution to reduce skill-related token consumption by ~76-83% during sprint workflows. Changes: - Add batch-execution.md skill with 4-phase protocol - Promote mcp-tools-reference and batch-execution to frontmatter for planner and orchestrator agents (auto-injected, zero re-read) - Replace "Skills to Load" with phase-based "Skill Loading Protocol" - Restructure planning-workflow.md Steps 8-10 for batch execution - Update agent matrix in CLAUDE.md and docs/CONFIGURATION.md - Add Phase-Based Skill Loading documentation section - Clean up .gitignore (transient files, dev symlinks) Token impact: - 6-issue sprint planning: ~76% reduction - 10-issue sprint planning: ~80% reduction - 8-issue status updates: ~83% reduction Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
60 lines
2.4 KiB
Markdown
60 lines
2.4 KiB
Markdown
---
|
|
description: Start sprint planning with AI-guided architecture analysis and issue creation
|
|
agent: planner
|
|
---
|
|
|
|
# Sprint Planning
|
|
|
|
## Skills Required
|
|
|
|
- skills/mcp-tools-reference.md (frontmatter — auto-injected)
|
|
- skills/batch-execution.md (frontmatter — auto-injected)
|
|
- skills/branch-security.md
|
|
- skills/repo-validation.md
|
|
- skills/input-detection.md
|
|
- skills/lessons-learned.md
|
|
- skills/wiki-conventions.md
|
|
- skills/task-sizing.md
|
|
- skills/issue-conventions.md
|
|
- skills/sprint-approval.md
|
|
- skills/planning-workflow.md
|
|
- skills/label-taxonomy/labels-reference.md
|
|
- skills/sprint-lifecycle.md
|
|
|
|
## Purpose
|
|
|
|
Initiate sprint planning session. The planner agent validates prerequisites, gathers requirements, searches lessons learned, creates wiki pages, and creates well-structured Gitea issues with proper dependencies and labels.
|
|
|
|
## Invocation
|
|
|
|
Provide sprint goals as natural language input, or prepare input via:
|
|
- `docs/changes/*.md` file with frontmatter
|
|
- Existing wiki proposal page
|
|
- Direct conversation
|
|
|
|
## Workflow
|
|
|
|
Execute the planning workflow as defined in `skills/planning-workflow.md`.
|
|
|
|
**Key steps:**
|
|
0. **Check Lifecycle State** - Execute `skills/sprint-lifecycle.md` check protocol. Expect idle state. Set `Sprint/Planning` after planning completes. Warn and stop if sprint is in another active state (unless `--force`).
|
|
1. Run pre-planning validations (branch, repo org, labels)
|
|
2. Detect input source (file, wiki, or conversation)
|
|
3. Search relevant lessons learned
|
|
4. Create/update wiki proposal and implementation pages
|
|
5. Perform architecture analysis
|
|
6. Create Gitea issues with wiki references (respecting task sizing rules)
|
|
7. Set up dependencies
|
|
8. Create or select milestone
|
|
9. Request explicit sprint approval
|
|
|
|
## Visual Output
|
|
|
|
```
|
|
╔══════════════════════════════════════════════════════════════════╗
|
|
║ 📋 PROJMAN ║
|
|
║ 🎯 PLANNING ║
|
|
║ [Sprint Name] ║
|
|
╚══════════════════════════════════════════════════════════════════╝
|
|
```
|