agentleFS
SafetyMPSafetyMP/HR-ERP/.cursor/skills/hr-foundation-governance/SKILL.md

hr-foundation-governance

Skill1 starsChanged 6 months agoApache-2.0View on GitHub

Agent harness foundation — manifest v4, hooks, lint, ALARP, Cursor native unlock, Phase 2 evidence. Use for .cursor/**, governance scripts, and meta docs.

The file

Files
SKILL.md

HR foundation governance

Cross-cutting harness work: manifest, hooks, lint, industry alignment. Human invokes — do not auto-run merge/deploy.

When

  • Editing .cursor/governance/**, scripts/governance-*, harness ADRs (0016–0019)
  • ALARP / Cordum L3 / NIST Agentic Profile evidence gaps
  • Plan Mode + governance:plan bridge for meta refactors
  • Evidence bundles, cloud session verify, team-map / agent-rules sync

Do not

  • Replace Cursor /multitask, /worktree, /best-of-n, Automations
  • Weaken payroll/Core HR invariants (repo-boundaries.mdc)
  • Duplicate DMAIC/PDCA checklists — use @hr-governance-learning for promote/reflect

Instructions

  1. Classify: npm run governance:lint
  2. Emit DAG: npm run governance:plan
  3. Parallel lanes: /multitask per @hr-orchestration-lanes
  4. DDL: /worktree + worktrees.json
  5. Cloud verify: environment.json → npm run governance:ci
  6. Evidence (ADR 0019): npm run governance:evidence collect|verify
  7. Cloud session ledger: npm run governance:cloud-session emit
  8. Handoff: specs/**/orchestrator-handoff.json with delegatedTaskPlan
  9. Team roster: agent-team-map.md
  10. CI: npm run governance:ci before merge

Phase 2 gates (ADR 0017–0019)

ADRFocus
0017Evidence bundle schema + lane signoffs
0018Adaptation plane — DMAIC/PDCA via @hr-governance-learning
0019Runtime parity, strict VDR (T1+), value/efficiency cross-cut
0020Collaboration plane — Harness HITL seven-phase loop

References

  • ADR 0016
  • ADR 0017
  • ADR 0018
  • ADR 0019
  • cursor-industry-alignment.md
  • cursor-3-native-runtime.md
  • agent-team-map.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.