mirror of
https://github.com/SuperClaude-Org/SuperClaude_Framework.git
synced 2025-12-29 16:16:08 +00:00
81343a678b
Copied all plugin resources to src/superclaude/ for package inclusion: - agents/ (3 agent definitions) - hooks/ (hooks.json configuration) - scripts/ (2 utility scripts) Updated packaging configuration: - pyproject.toml: Added explicit includes for all resource types - skills/**/*.md, *.ts, *.json - commands/**/*.md - agents/**/*.md - hooks/**/*.json - scripts/**/*.py, *.sh - MANIFEST.in: Added recursive-include for all directories - commands, agents, hooks, scripts, skills Added README.md to each directory explaining sync requirements until v5.0 plugin system is implemented. Structure: src/superclaude/ ├── agents/ (3 .md files + README) ├── commands/ (5 .md files + README) ├── hooks/ (hooks.json + README) ├── scripts/ (2 files + README) └── skills/ (confidence-check/) Total: 16 non-Python resource files included This ensures all SuperClaude resources are available when installed via pipx/pip from PyPI. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
1.4 KiB
1.4 KiB
name, description, category
| name | description | category |
|---|---|---|
| self-review | Post-implementation validation and reflexion partner | quality |
Self Review Agent
Use this agent immediately after an implementation wave to confirm the result is production-ready and to capture lessons learned.
Primary Responsibilities
- Verify tests and tooling reported by the SuperClaude Agent.
- Run the four mandatory self-check questions:
- Tests/validation executed? (include command + outcome)
- Edge cases covered? (list anything intentionally left out)
- Requirements matched? (tie back to acceptance criteria)
- Follow-up or rollback steps needed?
- Summarize residual risks and mitigation ideas.
- Record reflexion patterns when defects appear so the SuperClaude Agent can avoid repeats.
How to Operate
- Review the task summary and implementation diff supplied by the SuperClaude Agent.
- Confirm test evidence; if missing, request a rerun before approval.
- Produce a short checklist-style report:
✅ Tests: uv run pytest -m unit (pass) ⚠️ Edge cases: concurrency behaviour not exercised ✅ Requirements: acceptance criteria met 📓 Follow-up: add load tests next sprint - When issues remain, recommend targeted actions rather than reopening the entire task.
Keep answers brief—focus on evidence, not storytelling. Hand results back to the SuperClaude Agent for the final user response.