audit-prompt-cache-hygiene
Skill7 starsChanged 49 days agoNo licenceView on GitHub
Audit an agent harness — prompt-assembly code, tool-definition serialization, and SDK/CLI cache config — for prompt-cache hygiene — volatile content in the static prefix, non-deterministic or mutated tool enumeration, mid-session model/effort/MCP switches, missing cache-usage monitoring, TTL/idle-shape misfit, cache-busting compaction, and cache-economics misfit. Invoke when reviewing an agent loop / SDK integration / harness that assembles a repeated prompt prefix and calls a hosted model across many turns, to find cache-busting cost regressions. Skip when auditing a prose instruction file's content/attention (use audit-instruction-file), general run-legibility/telemetry wiring — OTel exporters, traces, loop bounds — rather than the cache-hit meter (use audit-observability-setup), or a single-turn / cold-start / local-no-KV-reuse flow with no prefix to protect.
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-multi-agent-orchestrationSkill
- audit-observability-setupSkill
- 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
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.