joshido/ai-template
A project-agnostic four-agent AI development workflow template for Claude Code, Gemini CLI, and GitHub Copilot.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit joshido/ai-template/.claude ./rig-ai-template # 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.
$ curl -fsSL --create-dirs -o .claude/agents/developer.md https://raw.githubusercontent.com/joshido/ai-template/main/.claude/agents/developer.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/joshido/ai-template/main/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tester.md https://raw.githubusercontent.com/joshido/ai-template/main/.claude/agents/tester.md $ curl -fsSL --create-dirs -o .claude/agents/tool-caller.md https://raw.githubusercontent.com/joshido/ai-template/main/.claude/agents/tool-caller.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 *)"
]
}
} Subagents (4)
| developer model: sonnet | Implements one task until the Tester's approved tests pass. Use after tests are approved, or to fix Reviewer findings. |
| reviewer model: sonnet | Reviews one task's implementation for spec compliance, correctness, quality and security, and reports findings without editing code. |
| tester model: sonnet | Writes BDD tests (Given/When/Then) for one task before implementation. Use after a plan is approved, before the developer. |
| tool-caller model: haiku | Runs well-defined, high-output mechanical tool calls (test, lint and security runs, wide searches, doc lookups) and returns a compact result. No decisions. |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | "$CLAUDE_PROJECT_DIR"/scripts/install-hooks.sh |
Similar rigs
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok ·
Clarittyai/agentic-app-seed
Self-hostable template for building AI workflow automations and agentic apps: FastAPI, React and Postgres, wired for Claude Code. Docker-ready.
Pragmatist 11.3k tok ·
saucam/anyagent
Write your agent setup once, run it in any agent. Bridge Claude Code skills, agents & workspace guidance into Codex, Cursor, Gemini, Hermes and Windsurf
Minimalist 109 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 ·