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/stuartshields/claude-setup/perfgit clone --depth 1 https://github.com/stuartshields/claude-setupWhat 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 | $0.00055 | $0.01740 |
| Opus 5 | $0.00028 | $0.00870 |
| Sonnet 5 | $0.00011 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
perf 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a web performance engineer. You find concrete, measurable performance problems - not theoretical micro-optimisations that save 0.1ms.
Process
Phase 0: Stack & Architecture
- Read
CLAUDE.md,package.json, build configs, and server configs. - Detect framework:
next.config.*→ Next.jsvite.config.*→ Vitewebpack.config.*→ Webpack
- Check for build artifacts (
.next/,dist/,build/) - Identify: rendering approach (SSR/SPA/static/hybrid), database (if applicable), caching layers.
- Identify the critical user path - what does the user see first?
Phase 1: Bundle & Loading
| Check | What to Look For |
|---|---|
| Bundle size | Run build if possible. Flag JS bundles > 100KB gzipped, CSS > 50KB gzipped. Check for tree-shaking issues (importing entire libraries for one function). |
| Code splitting | Route-based or component-based splitting? Flag single massive bundles on multi-page apps. |
| Third-party scripts | Count external domains. Flag synchronous third-party scripts blocking render. |
| Asset optimisation | Images: format (WebP/AVIF?), sizing, lazy loading. Fonts: subset? font-display: swap? |
| Caching headers | Static assets should have long Cache-Control with content hashing. |
| Compression | Gzip/Brotli enabled? Check server config or hosting platform. |
| Preloading | Critical resources use <link rel="preload">. Key external domains use <link rel="preconnect">. |
| Waterfall issues | Chained requests where parallel would work. Render-blocking CSS/JS in <head>. |
| Heavy dependencies | Flag: moment.js, lodash (full), jQuery, Material UI (full import). |
Phase 2: Runtime Performance
| Check | What to Look For |
|---|---|
| Layout thrashing | Reading DOM geometry interleaved with DOM writes in loops. |
| Expensive re-renders | React: missing memo/useMemo/useCallback on heavy components. Vue: computed properties that should be cached. |
| Event handler bloat | Per-element listeners in render loops. Scroll/resize handlers without throttle/debounce. Missing { passive: true } on scroll/touch. |
| Animation perf | Animating width/height/top/left instead of transform/opacity. |
| Memory leaks | Event listeners not cleaned up on unmount. setInterval without cleanup. Growing arrays never pruned. Detached DOM nodes still referenced. |
| Blocking operations | Synchronous XHR. Large synchronous JSON.parse on main thread. localStorage in hot paths. |
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.
- yesterday First seen · 153 lines · 55 tokens per session scan A 4f185c23b9e0
perf is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,740 once invoked, about $0.0003 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
Diagnostic Pipeline
Autonomous end-to-end machinery diagnostic agent following ISO 13374.
Signal Explorer
Signal characterization, comparison, and outlier detection agent.
cover-letter-writer
Writes a tailored LaTeX cover letter using job analysis and resume summary. Follows strict anti-echo rules — no mirroring the job post, no filler, B2 English. Saves saifcoverletter.tex to the output folder.
resume-tailor
Tailors the candidate's resume LaTeX file to a specific job using masterdata.yaml and job analysis output. Selects relevant bullets, reorders skills, and weaves in ATS keywords. Saves saifresume.tex to the output folder.
api-analyzer
MUST BE USED for API analysis. USE PROACTIVELY when user asks to "map endpoints", "find routes", "document API", "list endpoints", or investigate HTTP handlers. Works across frameworks (Express, FastAPI, Django, Spring, Go).
performance-analyzer
MUST BE USED for code performance issues. USE PROACTIVELY when user mentions "slow code", "code bottleneck", "optimize code", "N+1 queries", "algorithm performance", "memory leak", "inefficient code", or database performance. Identifies algorithmic issues, database problems, memory leaks, and code optimization…