matthieurosset/claude-custom-workflow
Multi-agent orchestration workflow template for Claude Code — one lead agent, six specialist subagents, guardrails, hook-driven quality gates, and a self-improving process loop. Battle-tested on a production app, generic and ready to adopt.
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 matthieurosset/claude-custom-workflow/.claude ./rig-claude-custom-workflow # 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 matthieurosset/claude-custom-workflow/.claude/skills/git-workflow-branch-worktree .claude/skills/git-workflow-branch-worktree $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/matthieurosset/claude-custom-workflow/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/matthieurosset/claude-custom-workflow/main/.claude/agents/builder.md $ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/matthieurosset/claude-custom-workflow/main/.claude/agents/debugger.md $ curl -fsSL --create-dirs -o .claude/agents/inspector.md https://raw.githubusercontent.com/matthieurosset/claude-custom-workflow/main/.claude/agents/inspector.md $ curl -fsSL --create-dirs -o .claude/agents/shipper.md https://raw.githubusercontent.com/matthieurosset/claude-custom-workflow/main/.claude/agents/shipper.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (1)
Subagents (5)
| architect model: opus | Intake + reconnaissance + implementation planner for the lead. Phased — Explore fan-out recon, brief + QUESTIONS_FOR_USER to the lead, iterate on the user's answers, then a concrete step-by-step plan |
| builder model: sonnet | Implementation specialist for the lead. Creates the git worktree, writes the code, applies the project's conventions (design system, i18n), commits in the worktree. Invokes the project skills at the r |
| debugger model: opus | Bug investigator for the lead. Takes a bug description (with optional stack trace / screenshot / repro steps), identifies the root cause via systematic debugging, and proposes a fix. Can apply small f |
| inspector model: opus | Quality gate for the lead. Runs after the builder, on the same worktree. Validates visual rendering, security (when applicable), code review, and static analysis — in parallel when safe. Returns a con |
| shipper model: sonnet | Delivery specialist for the lead. Merges the worktree to main, pushes to origin, deploys backend rules when relevant, and checks post-release analytics. Refuses any store/production deploy and force p |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| TaskCompleted | * | "$CLAUDE_PROJECT_DIR"/scripts/check_quality_gates.sh |
| SubagentStop | builder|debugger | "$CLAUDE_PROJECT_DIR"/scripts/check_quality_gates.sh --scan-all |
Similar rigs
itshig/AGENTS-template
Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.
Orchestrator 3.0k tok ·
yourconscience/tackroom
Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, agent roles, and memory — synced natively to Claude Code, Codex, OMP/Pi, OpenCode, Droid, and Hermes. Commit-pinned and audited externals.
Orchestrator 1.4k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
Pragmatist 3.0k tok ·
aravindhsampath/agentic-template
Cookie-cutter project template for an agentic development workflow: Claude Code architect + engineer subagents, Pi-based multi-model code review (Deepseek + Kimi), strict branch hygiene, declarative apply-standard script.
Pragmatist 2.5k tok ·