Exec Code — Testing & QA agent for Claude Code
Executant d'un lot CODE confie par /dispatch (implementation bornee, tests, refactor local).
How to install Exec Code
Installs to ~/.claude/agents/grozef-claude-config-exec-code.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Grozef/claude-config/HEAD/agents/exec-code.md -o ~/.claude/agents/grozef-claude-config-exec-code.md Restart Claude Code, or start a new session, for it to be picked up.
What Exec Code does
name: exec-code description: Executant d'un lot CODE confie par /dispatch (implementation bornee, tests, refactor local). Spec claire, aucun choix d'architecture. tools: Read, Edit, Write, Grep, Glob, Bash model: sonnet
Tu executes UN lot decrit par un brief. Tu ne vois pas la conversation d'origine : le brief est ta seule consigne.
Regles :
- Ne toucher QUE les fichiers autorises par le brief. Rien d'autre, meme pour « ameliorer ».
- Lire un fichier avant de le modifier. Lire le code
Alternatives in Testing & QA
- Track Spec — Track ID: {{TRACK_ID}} Type: {{TRACK_TYPE}} (feature bug chore refactor) Priority 31.9k ★
- Confluence Searcher — Searches Confluence and related tickets for product, architecture, rollout, and test-data context 548 ★
- Test Refactor Specialist.Agent — Improves test code quality and maintainability 225 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Exec Reviewer
Use after SPEC.md exists (product-interrogator has run) to review business value, scope, and buy-vs-build befo
Devex Reviewer
Use as the final step of the /sap-plan pipeline, after architecture and UX review, to flag developer-experienc
Worker Implementer
Implements a well-specified chunk of coding work - a spec's tickets, a component, a refactor - from a full bri
Spec Test Author
Writes scenario tests from OpenSpec specs, with restricted context kept independent from the implementer. Disp
Local Coder
Use for local code generation: implementing a function against a spec or failing test, refactor snippets, boil
Sol Implementer
High-complexity implementation lane running GPT-5.6 Sol via the OpenAI Codex CLI (codex exec), at whatever rea
Related Skills
Run Pipeline
Refactor → Security → Quality 3-stage 파이프라인 수동 실행. --full 로 Architecture 검증 추가, --with-tests 로 Test Generation
Cfn Arch
SPARC Architecture phase. Define component boundaries, interface contracts, integration points, DRY reuse BEFO
React Feature Kit
Spec-driven development for React: turn requirements into specifications, architecture plans, implementation,