audit-multi-agent-orchestration
Skill7 starsChanged 49 days agoNo licenceView on GitHub
Audit an existing multi-agent orchestration's coordination mechanics — typed vs prose handoffs, shared mid-run state, verifier/producer role separation, and loop bounds — and flag the structural smells that make multi-agent systems fail. Invoke when reviewing or hardening a harness that already runs more than one agent (orchestrator-worker, fan-out/synthesis, lead-and-teammates, generator-critic loops), including whether the verifier role is independent of the producer. Skip when deciding whether to go multi-agent at all or which topology (use architecture-committee), auditing the general completion-gating architecture — hooks, ledgers, graders, red-green anchoring (use audit-verification-gates), auditing security legs / prompt-injection (use audit-lethal-trifecta), or a single instruction file's prose (use audit-instruction-file).
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- architecture-committeeSkill
- audit-geo-contentSkill
- audit-github-actions-securitySkill
- audit-harness-safetySkill
- audit-instruction-fileSkill
- audit-lethal-trifectaSkill
- audit-mcp-serverSkill
- audit-memory-retrieval-integritySkill
- audit-observability-setupSkill
- audit-prompt-cache-hygieneSkill
- audit-prompt-hook-placementSkill
- audit-secret-exposureSkill
- audit-self-improvement-protocolSkill
- audit-skill-qualitySkill
- audit-supply-chain-sinksSkill
- audit-tool-definitionSkill
- audit-verification-gatesSkill
- compress-promptSkill
- conflicting-instruction-detectorSkill
- review-codeSkill
- write-skillSkill
- write-testsSkill
- write-tool-descriptionSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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
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.