Borrowing it
Nothing to install: this file belongs to WCAG-Compliance/wcagc-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WCAG-Compliance/wcagc-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/WCAG-Compliance/wcagc-mcpWrote 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/instructions/wcag-compliance/wcagc-mcp/claude-md)<a href="https://agentmods.dev/instructions/wcag-compliance/wcagc-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wcag-compliance/wcagc-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/wcag-compliance/wcagc-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wcag-compliance/wcagc-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00363 | $0.00363 |
| Opus 5.5 | $0.00145 | $0.00145 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
wcagc-mcp 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 1mo 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
CLAUDE.md — wcagc-mcp
Canonical rules for this service live in AGENTS.md — read it before changing anything here.
The one that bites
Changed anything in src/? Bump the version — with the script, never by hand:
npm run set-version 0.2.6
It updates all four places that must agree (package.json, server.json ×2, src/server.ts) and checks the result.
The version is the release trigger. Skip it and your change deploys to Fly while every npx @wcagc/mcp user stays on the old build, with nothing flagging the drift. npm run verify catches the four disagreeing with each other — it cannot catch a bump you never made.
Quick reminders (full detail in AGENTS.md)
- Never publish by hand — no
npm publish, nomcp-publisher publish, no pushing to the public mirror. CI owns all of it on a version change. - Hosted and local are one codebase. Never add a tool or behaviour to only one transport.
- Every scan result carries
coverageDisclaimer+standardin BOTHcontent[].textandstructuredContent. No score, no grade, no compliance verdict, anywhere. - No credentials as tool arguments — authenticated scans use the site's saved auth profile in the API.
GET /healthmust stay working and unauthenticated: it is Fly's probe and the hosted/npm parity check.- Verify with
npm run typecheck && npm run verify(node:test+ fixture API — no backend, no Playwright).
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.
- 1mo ago First seen · 25 lines · 363 tokens per session scan A 7cc0d7ed8a1f
wcagc-mcp CLAUDE.md is an instructions file published in the GitHub repository WCAG-Compliance/wcagc-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 363 tokens to every session, about $0.0015 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.