pierrebelin/claude-code-toolkit
Stop babysitting your coding agent. A Claude Code plugin that turns a business need into a spec, a plan and test-first code, audited before you commit. Built for DDD / clean-architecture repos.
field: unknown workflow: Testing & TDDPlanning & specsSecurity reviewGit & commitsRefactoring runs claude in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit pierrebelin/claude-code-toolkit/.claude ./rig-claude-code-toolkit # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit pierrebelin/claude-code-toolkit/presets/clean-architecture/skills/tests-contract-tests .claude/skills/tests-contract-tests $ npx degit pierrebelin/claude-code-toolkit/presets/clean-architecture/skills/tests-e2e-tests .claude/skills/tests-e2e-tests $ npx degit pierrebelin/claude-code-toolkit/presets/clean-architecture/skills/tests-integration-tests .claude/skills/tests-integration-tests $ npx degit pierrebelin/claude-code-toolkit/presets/clean-architecture/skills/tests-unit-tests .claude/skills/tests-unit-tests $ npx degit pierrebelin/claude-code-toolkit/skills/ask .claude/skills/ask $ npx degit pierrebelin/claude-code-toolkit/skills/business-spec .claude/skills/business-spec $ npx degit pierrebelin/claude-code-toolkit/skills/fix-bug .claude/skills/fix-bug $ npx degit pierrebelin/claude-code-toolkit/skills/implement-tdd .claude/skills/implement-tdd $ npx degit pierrebelin/claude-code-toolkit/skills/kit-init .claude/skills/kit-init $ npx degit pierrebelin/claude-code-toolkit/skills/knowledge-merge .claude/skills/knowledge-merge $ npx degit pierrebelin/claude-code-toolkit/skills/knowledge-sync .claude/skills/knowledge-sync $ npx degit pierrebelin/claude-code-toolkit/skills/learn .claude/skills/learn $ npx degit pierrebelin/claude-code-toolkit/skills/plan-implementation .claude/skills/plan-implementation $ npx degit pierrebelin/claude-code-toolkit/skills/quality-report .claude/skills/quality-report $ npx degit pierrebelin/claude-code-toolkit/skills/verify-ddd-tdd .claude/skills/verify-ddd-tdd
$ curl -fsSL --create-dirs -o .claude/agents/adversarial-reviewer.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/adversarial-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/ddd-tdd-auditor.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/ddd-tdd-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/knowledge-extractor.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/knowledge-extractor.md $ curl -fsSL --create-dirs -o .claude/agents/knowledge-merger.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/knowledge-merger.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-cycle.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/tdd-cycle.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-implementer.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/tdd-implementer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-test-author.md https://raw.githubusercontent.com/pierrebelin/claude-code-toolkit/main/agents/tdd-test-author.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (15)
tests-contract-teststests-e2e-teststests-integration-teststests-unit-testsaskbusiness-specfix-bugimplement-tddkit-initknowledge-mergeknowledge-synclearnplan-implementationquality-reportverify-ddd-tdd
Subagents (7)
| adversarial-reviewer model: opus | Tries to refute a spec, a plan or a batch sheet before code is written, when /business-spec or /plan-implementation delegates it. Reading only; returns closed questions ranked Blocking or Major. |
| ddd-tdd-auditor model: sonnet | Audits a .NET/DDD batch without ever modifying it when /verify-ddd-tdd is invoked. Reading, searching and running validations only. |
| knowledge-extractor model: sonnet | Drafts one bounded context of the knowledge base from the code when /knowledge-sync delegates it — staged drafts with provisional ids, never the base itself. |
| knowledge-merger model: sonnet | Drafts the merge of a delivered feature into the knowledge base when /knowledge-merge or the run-plan workflow delegates it — the spec's delta rewritten in the base's format, in the merge staging, nev |
| tdd-cycle model: sonnet | Writes the RED tests then the GREEN code of one TDD cycle in a single agent when the run-lot workflow runs a light batch; a checkpoint checked on the tree separates the two phases. |
| tdd-implementer model: sonnet | Writes the minimal production code that turns a red test green when /implement-tdd delegates the GREEN phase, then cleans up and states the access cost. |
| tdd-test-author model: sonnet | Writes the RED tests for a .NET/DDD behaviour when /implement-tdd delegates the test-first phase. |
Plugins (3)
context-band@cctoolkitknowledge-pane@cctoolkitrun-lot-pane@cctoolkit
Similar rigs
ritesh-firodiya/canon-cli
canon: your domain knowledge and AI rules, kept in your repos and enforced. Claude Code plugin + CLI.
Pragmatist 3.1k tok · · Q0
iurykrieger/claude-bedrock
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
Skill Collector 2.9k tok · · Q5
LilianPe/Orchestrator
Orchestrateur d'agents de code : un ticket Linear délégué devient une PR vérifiée, relue par une review IA puis par un humain, mergée par l'usine. Démon Node/TypeScript, Claude Code en sandbox rootless, GitHub App. Prototype, licence Elasti
Skill Collector 661 tok · · Q0
vuhuucuong/dotfiles
My Neovim config and relevant stuff
Pragmatist 3.9k tok · · Q15