vstakhovsky/shokunin-review
Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.
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 vstakhovsky/shokunin-review/.claude ./rig-shokunin-review # 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 vstakhovsky/shokunin-review/.claude/skills/ponytail-audit .claude/skills/ponytail-audit $ npx degit vstakhovsky/shokunin-review/.claude/skills/ponytail-debt .claude/skills/ponytail-debt $ npx degit vstakhovsky/shokunin-review/.claude/skills/ponytail-help .claude/skills/ponytail-help $ npx degit vstakhovsky/shokunin-review/.claude/skills/ponytail-review .claude/skills/ponytail-review $ npx degit vstakhovsky/shokunin-review/.claude/skills/ponytail .claude/skills/ponytail $ npx degit vstakhovsky/shokunin-review/.claude/skills/shokunin-gherkin .claude/skills/shokunin-gherkin $ npx degit vstakhovsky/shokunin-review/.claude/skills/shokunin-review .claude/skills/shokunin-review $ npx degit vstakhovsky/shokunin-review/.claude/skills/shokunin-score .claude/skills/shokunin-score $ npx degit vstakhovsky/shokunin-review/.claude/skills/shokunin-strategy .claude/skills/shokunin-strategy $ npx degit vstakhovsky/shokunin-review/.claude/skills/shokunin-verify .claude/skills/shokunin-verify $ npx degit vstakhovsky/shokunin-review/skills/shokunin-feedback-correction .claude/skills/shokunin-feedback-correction $ npx degit vstakhovsky/shokunin-review/skills/shokunin-review-prd .claude/skills/shokunin-review-prd
$ curl -fsSL --create-dirs -o .claude/agents/ai-safety-guardrails-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/ai-safety-guardrails-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/cost-roi-sanity-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/cost-roi-sanity-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/decision-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/decision-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/document-intake-agent.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/document-intake-agent.md $ curl -fsSL --create-dirs -o .claude/agents/evidence-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/evidence-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/finding-quality-auditor.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/finding-quality-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/metric-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/metric-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/opportunity-sizing-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/opportunity-sizing-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/output-guard.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/output-guard.md $ curl -fsSL --create-dirs -o .claude/agents/requirement-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/requirement-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/review-orchestrator.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/review-orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/review-spec-builder.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/review-spec-builder.md $ curl -fsSL --create-dirs -o .claude/agents/severity-calibrator.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/severity-calibrator.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-architect.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-architect.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-builder.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-builder.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-competitive-analyst.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-competitive-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-docs-curator.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-docs-curator.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-eval-calibrator.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-eval-calibrator.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-judge.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-judge.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-product-manager.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-product-manager.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-release-manager.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-release-manager.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-safety-judge.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-safety-judge.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-security-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-security-router.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-security-router.md $ curl -fsSL --create-dirs -o .claude/agents/shokunin-test-guardian.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/shokunin-test-guardian.md $ curl -fsSL --create-dirs -o .claude/agents/simpler-alternative-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/simpler-alternative-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/strategy-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/strategy-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/technical-feasibility-reviewer.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/technical-feasibility-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/validator-router.md https://raw.githubusercontent.com/vstakhovsky/shokunin-review/main/.claude/agents/validator-router.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 (12)
ponytail-auditponytail-debtponytail-helpponytail-reviewponytailshokunin-gherkinshokunin-reviewshokunin-scoreshokunin-strategyshokunin-verifyshokunin-feedback-correctionshokunin-review-prd
Subagents (29)
Slash commands (9)
/shokunin-eval/shokunin-improve/shokunin-rerun/shokunin-review-experiment/shokunin-review-prd/shokunin-review-rfc/shokunin-review-strategy/shokunin-review/shokunin-score
Similar rigs
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
saqie803/ponytail
Ship production-ready code with one line of AI-generated output, built for 20 agents and zero ceremony.
Pragmatist 714 tok ·
contextmux/contextmux
Turn a ticket into a reviewed pull request, under gates that stop work which drifted out of scope or weakened tests. Compiles one source of coding rules to CLAUDE.md, AGENTS.md, .cursor/rules and copilot-instructions.
Pragmatist 10.1k tok ·
Cygnux-Labs/Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
Skill Collector 2.1k tok ·