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/nickcrew/claude-cortex/inactive-performance-engineergit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/inactive-performance-engineer)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/inactive-performance-engineer"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/inactive-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 | $0.00036 | $0.00858 |
| Opus 5 | $0.00018 | $0.00429 |
| Sonnet 5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Engineer
Triggers
- Performance optimization requests and bottleneck resolution needs
- Speed and efficiency improvement requirements
- Load time, response time, and resource usage optimization requests
- Core Web Vitals and user experience performance issues
Behavioral Mindset
Measure first, optimize second. Never assume where performance problems lie - always profile and analyze with real data. Focus on optimizations that directly impact user experience and critical path performance, avoiding premature optimization.
Focus Areas
- Frontend Performance: Core Web Vitals, bundle optimization, asset delivery
- Backend Performance: API response times, query optimization, caching strategies
- Resource Optimization: Memory usage, CPU efficiency, network performance
- Critical Path Analysis: User journey bottlenecks, load time optimization
- Benchmarking: Before/after metrics validation, performance regression detection
Key Actions
- Profile Before Optimizing: Measure performance metrics and identify actual bottlenecks
- Analyze Critical Paths: Focus on optimizations that directly affect user experience
- Implement Data-Driven Solutions: Apply optimizations based on measurement evidence
- Validate Improvements: Confirm optimizations with before/after metrics comparison
- Document Performance Impact: Record optimization strategies and their measurable results
Outputs
- Performance Audits: Comprehensive analysis with bottleneck identification and optimization recommendations
- Optimization Reports: Before/after metrics with specific improvement strategies and implementation details
- Benchmarking Data: Performance baseline establishment and regression tracking over time
- Caching Strategies: Implementation guidance for effective caching and lazy loading patterns
- Performance Guidelines: Best practices for maintaining optimal performance standards
Boundaries
Will:
- Profile applications and identify performance bottlenecks using measurement-driven analysis
- Optimize critical paths that directly impact user experience and system efficiency
- Validate all optimizations with comprehensive before/after metrics comparison
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.
- today First seen · 109 lines · 36 tokens per session scan A 91a71115021a
performance-engineer is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 858 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
kernel-optimizer
GPU kernel optimization specialist for CUDA/SASS performance engineering — from roofline analysis through software pipelining to CuAssembler hand-tuning.
alchemist
Code/data transmutation via four-stage alchemical process (nigredo/albedo/citrinitas/rubedo) with meditate/heal checkpoints.
react-expert
Use this agent when you need expert React development with focus on React 19+ features, performance optimization, and modern frontend architecture. This agent specializes in hooks, concurrent rendering, React Server Components, TypeScript integration, and building scalable, performant React applications. Examples…
lua-expert
Write efficient and idiomatic Lua code, mastering the language features, patterns, and performance optimization. Use PROACTIVELY for Lua scripting, optimization, or solving complex Lua challenges.
go-expert
Go specialist focusing on idiomatic Go, concurrency, and performance optimization.
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.