Governance Skill

Enforces engineering standards and code quality policies with parallel agent execution for context efficiency.

Standards Document: standards.md (starter default — replace with your own) Audit Script: npm run audit:standards Full Protocol: agent-prompt.md

Execution Model (v2.1)

Type: Delegated Execution — delegates to the built-in reviewer subagent type.

This skill uses the reviewer subagent (available in all Claude Code installations — no custom agent required):

1. Spawn the reviewer agent
2. Delegate the governance task with instructions from agent-prompt.md
3. Await completion
4. Report the structured summary to the user

Token Efficiency

How to Invoke

When this skill is triggered, read agent-prompt.md for the full protocol, then delegate:

Code Review

javascript
1Task({
2  description: "Governance code review",
3  prompt: `[See agent-prompt.md for full instructions]
4Review the following files for standards compliance:
5- [list files or PR description]
6
7Execute full code review workflow:
81. Run standards audit
92. Check each file against standards.md
103. Fix ALL issues immediately (zero deferral)
114. Return structured summary`,
12  subagent_type: "reviewer"
13})

Pre-Commit Check

javascript
1Task({
2  description: "Pre-commit governance",
3  prompt: `[See agent-prompt.md for full instructions]
4Run pre-commit governance checks:
51. typecheck, lint, format:check, test
62. Check for untracked source files
73. Return pass/fail with specific failures`,
8  subagent_type: "reviewer"
9})

Retrospective

javascript
1Task({
2  description: "Run retrospective",
3  prompt: `[See agent-prompt.md for full instructions]
4Run retrospective for [topic/sprint]:
51. Analyze completed issues
62. Gather metrics
73. Write report
84. Return summary`,
9  subagent_type: "reviewer"
10})

Quick Reference

Pre-Commit Checklist

[ ] npm run typecheck
[ ] npm run lint
[ ] npm run test
[ ] npm run audit:standards
[ ] No console.log statements
[ ] No hardcoded secrets

Compliance Check

bash
1npm run audit:standards
2node scripts/governance-check.mjs

Full agent protocol, anti-pattern tables, and output format in agent-prompt.md Version 2.1.0 — Structural cleanup: flat layout, built-in reviewer agent, standards.md default added