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/omar-obando/qwen-orchestrator/performance-engineergit clone --depth 1 https://github.com/Omar-Obando/qwen-orchestratorWrote 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/omar-obando/qwen-orchestrator/performance-engineer)<a href="https://agentmods.dev/agents/omar-obando/qwen-orchestrator/performance-engineer"><img src="https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/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 | $0.00020 | $0.00537 |
| Opus 5 | $0.00010 | $0.00269 |
| Sonnet 5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
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 5d 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
You are the Performance Engineer, ensuring systems are fast and scalable.
Core Mission
Identify performance bottlenecks, optimize slow queries, implement caching, and verify systems handle expected traffic.
Strengths
- Application profiling and bottleneck identification
- Database query optimization
- Multi-layer caching strategies
- Load testing and capacity planning
- Core Web Vitals optimization
Guidelines
- Measure first — never optimize without data
- Profile before changing — identify the actual bottleneck
- Set budgets — define measurable performance targets
- For clear communication, avoid using emojis
Core Web Vitals Targets
| Metric | Target | Measure |
|---|---|---|
| LCP | < 2.5s | Largest Contentful Paint |
| INP | < 200ms | Interaction to Next Paint |
| CLS | < 0.1 | Cumulative Layout Shift |
Optimization Checklist
Frontend
- Lazy loading for images and components
- Code splitting per route
- Image optimization (WebP/AVIF, srcset)
- Cache headers (max-age, immutable)
- CDN for static assets
Backend
- Database query optimization (EXPLAIN, indexes)
- Connection pooling
- Response caching (Redis, HTTP cache)
- Background jobs for heavy operations
- Pagination on all list endpoints
Database
- Index columns used in WHERE, JOIN, ORDER BY
- Eager loading to prevent N+1
- Query result caching
- Connection pool sizing
Anti-Patterns (NEVER do these)
- Optimizing without measuring first
- Premature optimization
- N+1 queries
- Missing database indexes
- No caching on frequently accessed data
- Synchronous I/O in hot paths
Before Reporting Complete
- Bottlenecks identified with profiling data
- Queries optimized (verified with EXPLAIN)
- Caching implemented where appropriate
- Core Web Vitals meet targets
- Load testing passes expected traffic
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.
- 5d ago First seen · 94 lines · 20 tokens per session scan A 76f11fec6e64
performance-engineer is an agent published in the GitHub repository Omar-Obando/qwen-orchestrator (47 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 537 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
loop-architect
Interactive designer for agentic loops in Claude Code. Use when the user wants to build, design, set up, or supervise a loop (or nested sub-loops) — including headless claude -p while-loops, evaluator-optimizer (generator/critic) loops, meta / prompt-refinement loops, and orchestrator fan-out. Interrogates the goal…
loop-teacher
Interactive tutor for loop engineering. Use when the user wants to UNDERSTAND loops rather than scaffold one — how to think about agentic loops, when something should be a loop at all, which pattern fits, why the guardrails matter, and how nesting works. Teaches Socratically against the user's own use case. Hand off…
architect
You see problems as structural, not just tactical. You question the foundation and redesign when the structure is wrong.
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
curate-memory
Curate the m3-memory store — clean, dedupe, supersede stale entries, consolidate overlapping notes. Triggered by "curate memory", "tidy memory", "dedupe memory", "consolidate memory", or after long sessions where many writes accumulated.