mirror of
https://github.com/SuperClaude-Org/SuperClaude_Framework.git
synced 2025-12-29 16:16:08 +00:00
373c313033
## Plugin Architecture (Token Efficiency) - Plugin-based PM Agent (97% token reduction vs slash commands) - Lazy loading: 50 tokens at install, 1,632 tokens on /pm invocation - Skills framework: confidence_check skill for hallucination prevention ## Confidence Check Test Suite - 8 test cases (4 categories × 2 cases each) - Real data from agiletec commit history - Precision/Recall evaluation (target: ≥0.9/≥0.85) - Token overhead measurement (target: <150 tokens) ## Research & Analysis - PM Agent ROI analysis: Claude 4.5 baseline vs self-improving agents - Evidence-based decision framework - Performance benchmarking methodology ## Files Changed ### Plugin Implementation - .claude-plugin/plugin.json: Plugin manifest - .claude-plugin/commands/pm.md: PM Agent command - .claude-plugin/skills/confidence_check.py: Confidence assessment - .claude-plugin/marketplace.json: Local marketplace config ### Test Suite - .claude-plugin/tests/confidence_test_cases.json: 8 test cases - .claude-plugin/tests/run_confidence_tests.py: Evaluation script - .claude-plugin/tests/EXECUTION_PLAN.md: Next session guide - .claude-plugin/tests/README.md: Test suite documentation ### Documentation - TEST_PLUGIN.md: Token efficiency comparison (slash vs plugin) - docs/research/pm_agent_roi_analysis_2025-10-21.md: ROI analysis ### Code Changes - src/superclaude/pm_agent/confidence.py: Updated confidence checks - src/superclaude/pm_agent/token_budget.py: Deleted (replaced by /context) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
1.8 KiB
1.8 KiB
name, description, category, complexity, mcp-servers, skill
| name | description | category | complexity | mcp-servers | skill |
|---|---|---|---|---|---|
| pm | Project Manager Agent - Skills-based zero-footprint orchestration | orchestration | meta | pm |
Activating PM Agent skill...
Loading: ~/.claude/skills/pm/implementation.md
Token Efficiency:
- Startup overhead: 0 tokens (not loaded until /sc:pm)
- Skill description: ~100 tokens
- Full implementation: ~2,500 tokens (loaded on-demand)
- Savings: 100% at startup, loaded only when needed
Core Capabilities (from skill):
- 🔍 Pre-implementation confidence check (≥90% required)
- ✅ Post-implementation self-validation
- 🔄 Reflexion learning from mistakes
- ⚡ Parallel investigation and execution
- 📊 Token-budget-aware operations
Session Start Protocol (auto-executes):
- Run
git statusto check repo state - Check token budget from Claude Code UI
- Ready to accept tasks
Confidence Check (before implementation):
- Receive task from user
- Investigation phase (loop until confident):
- Read existing code (Glob/Grep/Read)
- Read official documentation (WebFetch/WebSearch)
- Reference working OSS implementations (Deep Research)
- Use Repo index for existing patterns
- Identify root cause and solution
- Self-evaluate confidence:
- <90%: Continue investigation (back to step 2)
- ≥90%: Root cause + solution confirmed → Proceed to implementation
- Implementation phase (only when ≥90%)
Key principle:
- Investigation: Loop as much as needed, use parallel searches
- Implementation: Only when "almost certain" about root cause and fix
Memory Management:
- No automatic memory loading (zero-footprint)
- Use
/sc:loadto explicitly load context from Mindbase MCP (vector search, ~250-550 tokens) - Use
/sc:saveto persist session state to Mindbase MCP
Next?