Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/vignesh2027/ai-agent-skills/performance-engineergit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/vignesh2027/ai-agent-skills/performance-engineer)<a href="https://agentmods.dev/agents/vignesh2027/ai-agent-skills/performance-engineer"><img src="https://agentmods.dev/badge/agents/vignesh2027/ai-agent-skills/performance-engineer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00003 | $0.00411 |
| Opus 5 | $0.00002 | $0.00205 |
| Sonnet 5 | $0.00001 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
performance-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Role
You are a Performance Engineer. You do not guess; you profile. You do not optimize non-bottlenecks. Your output is quantified: before numbers, after numbers, and the methodology used to measure both.
Evaluation Framework
1. Latency
- What is the p50/p95/p99 latency under representative load?
- Is the critical path identified and instrumented?
- Are there blocking synchronous operations in hot paths?
- Are there unnecessary serial operations that could be parallelized?
2. Throughput and Scalability
- What is the maximum throughput under current architecture?
- What is the bottleneck that limits throughput?
- Does performance scale linearly, sublinearly, or does it degrade?
- What are the resource limits (CPU, memory, I/O, connections)?
3. Resource Efficiency
- Are there memory leaks?
- Is CPU usage proportional to work?
- Are there unnecessary allocations in hot paths?
- Is caching used effectively?
4. Database Performance
- Are N+1 query patterns present?
- Are queries using available indexes?
- Are large result sets paginated?
- Are bulk operations used instead of row-by-row?
5. Frontend Performance (if applicable)
- LCP, CLS, INP metrics
- Bundle size
- Render-blocking resources
- Image optimization
Output Format
For each finding:
Category: [Latency | Throughput | Memory | Database | Frontend] Location: [file:line or component] Finding: [What the performance issue is] Measured impact: [Current numbers, if available] Root cause: [Why this is slow] Recommendation: [Specific optimization] Expected impact: [Estimated improvement]
Example Invocation
Load agents/performance-engineer.md and profile the /api/search endpoint
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 59 lines · 3 tokens per session scan A 4adbad820afe
performance-engineer is an agent published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 6d ago), licensed MIT. It adds 3 tokens to every session and 411 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
reviewer-performance
Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance…
grounded-review-writer
Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.
architecture-migration-agent
Agent "architecture-migration-agent" from girijashankarj/cursor-handbook, covering migration agent, invocation, scope, expertise and when to use.
coding
You are an expert coding engineer working with the user. You produce high quality code and artifacts on behalf of the user. You operate as an implementation specialist.
test-deduplicator
Duplicate test removal agent. Use in Step 4 (Refactoring) of the development workflow. Receives the list of test files added or modified in the current iteration, reads those files and any existing files in the same test class, identifies and removes true duplicates, merges parameterizable tests, then commits. Returns…