From docs-governance
Maintains AGENTS.md, AGENT_LEARNINGS.md, AGENT_REQUESTS.md, and CONTRIBUTING.md governance files in sync with codebase changes. Use when updating governance files, during sprint reviews, or after structural changes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/docs-governance:maintaining-agents-mdThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Scope**: $ARGUMENTS
Scope: $ARGUMENTS
Keeps agent governance files synchronized with codebase state. Detects stale references, missing updates, and promotion candidates.
| File | Authority | Purpose |
|---|---|---|
AGENTS.md | Behavioral | Rules, role boundaries, compliance requirements |
CONTRIBUTING.md | Technical | Workflows, commands, coding standards |
AGENT_LEARNINGS.md | Knowledge | Accumulated patterns and solutions |
AGENT_REQUESTS.md | Escalation | Active blockers requiring human input |
AGENT_LEARNINGS.md to .claude/rules/make validate pipeline or Makefile changesaudit (default)Scan governance files for staleness and inconsistencies.
Checks:
src/, docs/, tests/ paths.
Verify each path still exists.CONTRIBUTING.md command reference table. Verify
each make recipe exists in Makefile.AGENT_LEARNINGS.md. If ralph/docs/LEARNINGS.md exists, check it too.AGENT_REQUESTS.md entries — flag any whose
referenced files/issues no longer exist..claude/skills/ inventory.Output: Findings table with file, line, issue type, description.
syncFix staleness found by audit. For each finding:
promoteEvaluate AGENT_LEARNINGS.md entries for promotion per the criteria in
.claude/rules/compound-learning.md (3rd occurrence → rule, recurring → skill).
Procedure:
AGENT_LEARNINGS.md entries.claude/rules/fullRun all three modes in sequence: audit → sync → promote.
When multiple files need updates, follow this order to prevent hierarchy conflicts:
.claude/rules/compound-learning.md — promotion pathFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.
npx claudepluginhub qte77/claude-code-plugins --plugin docs-governance