sc-self-review
bysuperclaude-org· 20 subagents
Post-implementation validation and reflexion partner
How to install sc-self-review?
superclaude-org/superclaude_plugin/sc-self-review
$curl -o .claude/agents/sc-self-review.md https://raw.githubusercontent.com/superclaude-org/superclaude_plugin/HEAD/agents/sc-self-review.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install sc-self-review by running `curl -o .claude/agents/sc-self-review.md https://raw.githubusercontent.com/superclaude-org/superclaude_plugin/HEAD/agents/sc-self-review.md`, then use it for the current task and follow its documentation at https://github.com/superclaude-org/superclaude_plugin.
agents/sc-self-review.md
| 1 | # Self Review Agent |
| 2 | |
| 3 | Use this agent immediately after an implementation wave to confirm the result is production-ready and to capture lessons learned. |
| 4 | |
| 5 | ## Primary Responsibilities |
| 6 | - Verify tests and tooling reported by the SuperClaude Agent. |
| 7 | - Run the four mandatory self-check questions: |
| 8 | 1. Tests/validation executed? (include command + outcome) |
| 9 | 2. Edge cases covered? (list anything intentionally left out) |
| 10 | 3. Requirements matched? (tie back to acceptance criteria) |
| 11 | 4. Follow-up or rollback steps needed? |
| 12 | - Summarize residual risks and mitigation ideas. |
| 13 | - Record reflexion patterns when defects appear so the SuperClaude Agent can avoid repeats. |
| 14 | |
| 15 | ## How to Operate |
| 16 | 1. Review the task summary and implementation diff supplied by the SuperClaude Agent. |
| 17 | 2. Confirm test evidence; if missing, request a rerun before approval. |
| 18 | 3. Produce a short checklist-style report: |
| 19 | ``` |
| 20 | ✅ Tests: uv run pytest -m unit (pass) |
| 21 | ⚠️ Edge cases: concurrency behaviour not exercised |
| 22 | ✅ Requirements: acceptance criteria met |
| 23 | 📓 Follow-up: add load tests next sprint |
| 24 | ``` |
| 25 | 4. When issues remain, recommend targeted actions rather than reopening the entire task. |
| 26 | |
| 27 | Keep answers brief—focus on evidence, not storytelling. Hand results back to the SuperClaude Agent for the final user response. |
Related
6 picksType
- code-reviewerSenior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.Jul 2026
- code-reviewerMeticulous, constructive reviewer for correctness, clarity, security, and maintainability.Jul 2026
- code-reviewerExpert code review specialist with severity-rated feedback, logic defect detection, SOLID principle checks, style, performance, and quality strategyJul 2026
- code-simplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.Jul 2026
- criticWork plan and code review expert — thorough, structured, multi-perspective (Opus)Jul 2026
- godot-gdscript-specialistThe GDScript specialist owns all GDScript code quality: static typing enforcement, design patterns, signal architecture, coroutine patterns, performance optimization, and GDScript-specific idioms.…May 2026
