jkutasi/claude-get-started-prd-framework
Multi-agent PRD framework template for Claude Code Agent Teams. Test-first workflow, multi-model peer review, 10-phase slice lifecycle.
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 jkutasi/claude-get-started-prd-framework/.claude ./rig-claude-get-started-prd-framework # 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 jkutasi/claude-get-started-prd-framework/.claude/skills/frontier-workflow .claude/skills/frontier-workflow $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/jkutasi/claude-get-started-prd-framework/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/utility.md https://raw.githubusercontent.com/jkutasi/claude-get-started-prd-framework/main/.claude/agents/utility.md $ curl -fsSL --create-dirs -o .claude/agents/worker.md https://raw.githubusercontent.com/jkutasi/claude-get-started-prd-framework/main/.claude/agents/worker.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 (3)
| orchestrator model: claude-fable-5 | Fable 5 project orchestrator. Owns routing, risk, integration, and delivery. |
| utility model: haiku | Haiku mechanical worker for search, summaries, inventories, logs, formatting, and provable edits. |
| worker model: claude-sonnet-5 | Sonnet 5 implementation worker for clear, bounded engineering tasks. |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup|clear|compact | bash hooks/session-start.sh |
Similar rigs
ameya-vichare/claude-sdd-starter
A platform-agnostic Claude Code setup for engineering teams, using an interactive setup wizard that tailors everything to your project and provides a spec-driven feature development workflow.
Orchestrator 2.3k tok ·
RandallLiuXin/GodotMaker
Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode
Orchestrator 1.5k tok ·
fjerbi/claude-code-arsenal
A tested Claude Code operating system for efficient, reliable, and focused software engineering. Includes global instructions, workflows, rules, and tools designed to minimize wasted tokens, prevent hallucinations and unnecessary loops, enf
YOLO Cowboy 4.0k tok ·
Gidntsquia/claude-config
My Claude Code agents, skills and settings
Pragmatist 673 tok ·