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 instructions/nucliweb/webperf-snippets/claude-mdgit clone --depth 1 https://github.com/nucliweb/webperf-snippetsWhat 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 | $0.00853 | $0.00853 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
webperf-snippets CLAUDE.md 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
WebPerf Snippets is a curated collection of web performance measurement JavaScript snippets designed for use in browser consoles or Chrome DevTools. The project is a documentation website built with Next.js and Nextra, serving as a comprehensive resource for web performance analysis tools.
Architecture
Technology Stack
- Framework: Next.js 13+ with Nextra documentation theme
- Theme: nextra-theme-docs for documentation layout
- Media: Cloudinary integration via next-cloudinary for optimized images/videos
- Deployment: Vercel
- Analytics: Google Analytics and DebugBear monitoring
Project Structure
pages/
├── _app.js # Next.js app wrapper with analytics scripts
├── _meta.json # Top-level navigation configuration
├── index.mdx # Homepage with introduction and video
├── CoreWebVitals/ # LCP, CLS, and related metrics
│ ├── _meta.json
│ └── *.mdx
├── Loading/ # Resource loading, TTFB, scripts, fonts analysis
│ ├── _meta.json
│ └── *.mdx
└── Interaction/ # User interaction and animation frame metrics
├── _meta.json
└── *.mdx
theme.config.jsx # Nextra theme configuration (branding, SEO, footer)
next.config.js # Next.js + Nextra configuration with redirects
Content Organization
The documentation uses Nextra's file-system based routing:
- Each category has its own directory under
pages/ - Individual snippets are documented in
.mdxfiles with executable JavaScript code - Navigation structure is controlled by
_meta.jsonfiles in each directory - All snippets are JavaScript code meant for Chrome DevTools console execution
Key Configuration Files
- theme.config.jsx: Site branding (logo SVG), SEO meta tags, Open Graph settings, footer, sidebar configuration
- pages/_app.js: Next.js app wrapper that includes DebugBear and Google Analytics scripts
- next.config.js: Nextra integration and URL redirects for renamed pages
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.
- 2d ago First seen · 111 lines · 853 tokens per session scan A c1a209799aee
webperf-snippets CLAUDE.md is an instructions file published in the GitHub repository nucliweb/webperf-snippets (1,445 stars, last pushed 1mo ago), licensed MIT. It adds 853 tokens to every session, about $0.0043 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 instructions, from other repositories
hotpath-rs AGENTS.md
AGENTS.md instructions for pawurb/hotpath-rs, covering agents.md, project overview, reference docs, development commands and profiling modes are combined via features, e.g.
vscode-angular-snippets AGENTS.md
Instructions for johnpapa/vscode-angular-snippets, covering angular snippets for vs code — agent guide, repository structure, tech stack, build & run and test in browser (vscode.dev mode).
vscode-angular-snippets copilot-instructions.md
Instructions for johnpapa/vscode-angular-snippets, covering copilot instructions — vscode-angular-snippets, project type, snippet conventions, prefix naming and snippet body.
web-worker-patterns copilot-instructions.md
Instructions for damiansire/web-worker-patterns, covering persona, examples, resources, best practices & style guide and coding style guide.
web-worker-patterns AGENTS.md
Instructions for damiansire/web-worker-patterns, covering agents.md, estado actual (uno y uno), la regla de oro (no negociable) and gates antes de cerrar cualquier cambio.
flameox AGENTS.md
Instructions for morluto/flameox, covering repository guidelines, product direction, project structure & module organization, build, test, and development commands and coding style & naming conventions.