--- description: Review code for quality, security, and…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Review code for quality, security, and best practices allowed-tools: Read, Grep, Glob, Bash(git diff: ), Bash(git log: ) --- # Code Review Review the specified code or recent changes for quality and best practices. ## Context - Current git status: ! git status --short - Recent changes: ! git diff HEAD~1 --stat ## Review Checklist ### 1. Code Quality - [ ] Code is readable and well-organized - [ ] Functions are small and focused - [ ] Variable and function names are descriptive - [ ] No unnecessary complexity ### 2. Security - [ ] No hardcoded secrets or credentials - [ ] Input validation is present - [ ] No SQL injection vulnerabilities - [ ] Proper error handling (no sensitive data in errors) ### 3. Performance - [ ] No obvious performance issues - [ ] Appropriate data structures used - [ ] No unnecessary loops or iterations ### 4. Testing - [ ] Tests are present for new code - [ ] Edge cases are covered - [ ] Tests are meaningful and not trivial ### 5. Best Practices - [ ] Follows project conventions - [ ] Proper error handling - [ ] No deprecated APIs used ## Output Format Organize feedback by priority: - Critical : Must fix before merge - War
claude-code
More testing loops
--- description: Boot TricorderKit session — charge le…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Boot TricorderKit session — charge le contexte, HOT CACHE, patterns d'erreurs, état du projet. Séquence tier 1/2/3. allowed-tools: Read, Bash, mcp obsidian-claude-vault read note, mcp obsidian-claude-vault patch note --- Exécute la séquence de démarrage TricorderKit v0.9. ## Séquence obligatoire ### TIER 1 — Toujours (~500 tokens) 1. Lire BOOT SUMMARY.md — résumé exécutif : version, commit, tests, Docker, prochaines tâches 2. Lire tasks/lessons.md — règles préventives actives (LESSON-001 à NNN) Si TIER 1 + lessons.md suffisent pour la demande → aller directement à l'action. ### TIER 2 — Si TIER 1 insuffisant (~2 500 tokens) 3. Lire .planning/STATE.md — état détaillé du projet 4. Lire .planning/TASKS.md — pending/in progress uniquement (exclure ✅) 5. Lire .planning/DECISIONS.md — 5 dernières entrées uniquement ### TIER 3 — À la demande (~10 000 tokens) 6. docs/00 WHAT IS TRICORDERKIT.md 7. docs/01 HOW IT WORKS.md 8. docs/02 WHAT IS IN PLACE.md 9. docs/03 WHAT TO DO NEXT.md 10. docs/04 LLM OPERATING GUIDE.md 11. docs/06 workflow standard.md ## HOT CACHE Obsidian (si MCP disponible) - Lire 00 SYSTEM/05 Hot Cache/HOT CACHE.md dans le
testingmedium risk
--- description: Bug fix workflow — root-cause analysis…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Bug fix workflow — root-cause analysis, reproduce-first regression test, fix, review, and verification. argument-hint: "<bug description>" allowed-tools: [Agent, Read, Glob, Grep, Bash, Edit, Skill] --- # /fix — Diagnose and fix a bug (reproduce-first) Bug: $ARGUMENTS You are the tech lead. Fix the bug properly: find the root cause, write a failing test, fix, prove the test passes, and audit. ## Steps 1. Diagnose. Run the root-cause-analyst agent on $ARGUMENTS. It returns the root cause with file:line , the blast radius, and a regression-test design (name, location, fixtures, assertion). If it cannot find the cause confidently, surface that to the user before changing code. 2. Reproduce. Invoke the test-engineer agent to write the regression test exactly as designed and run it — confirm it fails for the right reason on current code. (Skip only if the user explicitly opts out of a test.) 3. Fix. Invoke the appropriate expert ( backend-engineer / frontend-engineer / ai-engineer / database-engineer ) with the root cause and the concrete fix. Address sibling occurrences if the analyst found them. 4. Verify. Re-run the regressi
testinghigh risk
<!-- MAINTAINER NOTE (this comment is stripped from…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
<!-- MAINTAINER NOTE (this comment is stripped from the model's context, so it is a safe place for meta-notes). This is a TEMPLATE. Replace every [CUSTOMIZE: ...] and [PLACEHOLDER] with your project's real values, and delete guidance you do not need. Keep this file SHORT (target 150 to 200 lines). CLAUDE.md is loaded into context on every turn, so every line competes for attention. Apply the prune test to each line: "would removing this cause a wrong action?" If no, cut it or push it down: - Procedures and workflows -> .claude/skills/<name>/SKILL.md - File-type / layer rules -> .claude/rules/<name>.md (path-scoped) - When-to-use-which-agent -> docs/AGENT-GUIDE.md CLAUDE.md holds only the always-true, project-wide essentials. --> # [PROJECT NAME] - Claude Code Instructions > Multi-agent orchestration project. Cross-tool config in AGENTS.md ; full guides in docs/ ; enforcement rules in .claude/rules/ . ## Quick start (every session) 1. Read today's work record: docs/workrecords/work-record-YYYY-MM-DD.md (create it if missing). 2. Understand current state before changing anything. Verify names, paths, and configs from source; never assume them. 3
testinghigh risk