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

hr-swarm-governance

Skill1 starsChanged 6 months agoApache-2.0View on GitHub

HR ERP multi-agent FinOps, collaboration post-mortems, contributor triage, and golden-thread audits. Use when ≥2 delegated Tasks on one feature, swarm retrospectives, or human-authored PR/issue handoffs.

The file

Files
SKILL.md

HR swarm governance

Use this skill when

  • Two or more Cursor Tasks on one feature thread (FinOps note required)
  • Human Lead requests collaboration audit or golden-thread scoring
  • Community PR triage with orchestrator JSON handoff

Do not use this skill when

  • Single-thread implementation
  • T0–T3 without swarm or post-mortem trigger

Instructions

  1. Emit FinOps checkpoint: model tier per function lane; context budget per Task (no plugin dump).
  2. Post-mortem: golden-thread-trace-table.md; score DAG integrity (lanes invoked vs plan).
  3. Handoff JSON: function ids only — ban archived hr-erp-* skill names in prompts.
  4. governance:ci strict — do not waive on external PRs.
  5. Ping-pong breaker: 3 same-domain fix: commits → escalate Human.

Resources

  • references/finops-swarm.md
  • references/collaboration-audit.md
  • docs/meta/global-agent-governance-overlay.md

Limitations

  • Cursor Task cost governance only — not in-app inference budgets (ADR 0001)

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.