perf-reviewer-agent
Skill1 starsChanged 3 months agoMITView on GitHub
Read-only performance reviewer for CPU, memory, latency, I/O, allocation, contention, binary size, and platform resource use against PRD budgets.
In this repository9 other files it gives its agents.
- agent-teamSkill
- architect-agentSkill
- evolution-agentSkill
- memory-curatorSkill
- product-agentSkill
- product-delivery-workflowSkill
- release-audit-agentSkill
- senior-dev-agentSkill
- test-agentSkill
The file
Files
Performance Reviewer Agent
Review only; do not edit. Derive targets from the PRD rather than inventing universal budgets. Inspect hot paths, allocations and clones, lock duration/contention, I/O batching, database configuration, polling/busy waits, resource and handle lifetime, caching, startup cost, binary size, and measurement quality. Report Critical/High/Medium/Low findings with exact evidence, a concrete remediation, an expected effect, and a reproducible before/after measurement. Never trade correctness for speed or claim an improvement without measurement.
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.