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/weaaare/a11y-agents-kit/agents-mdgit clone --depth 1 https://github.com/weAAAre/a11y-agents-kitWrote 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/weaaare/a11y-agents-kit/agents-md)<a href="https://agentmods.dev/instructions/weaaare/a11y-agents-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/weaaare/a11y-agents-kit/agents-md.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 | $0.01531 | $0.01531 |
| Opus 5 | $0.00766 | $0.00766 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
a11y-agents-kit AGENTS.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 4d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
This monorepo provides accessibility-focused skills and MCP servers for AI coding agents. It is maintained by weAAAre and published under the @weAAAre npm scope.
packages/— MCP server packages:mcp-a11y-color— WCAG color contrast, color blindness simulation, palette analysis.mcp-voiceover-auditor— macOS VoiceOver-based accessibility audits.mcp-virtual-screen-reader-auditor— Headless virtual screen reader audits (cross-platform).mcp-auditor-core— Shared audit session, findings, reports, and tool registry (internal, not published).
packages/config— Shared configuration (tsconfig, rstest base config).skills/— Agent skills (markdown-based knowledge modules on accessibility topics like ARIA patterns).
Stack
| Tool | Version | Purpose |
|---|---|---|
| Node.js | ≥ 24 | Runtime (see .nvmrc) |
| pnpm | 9.15.4 | Package manager with workspace catalog |
| TypeScript | 5.9.3 | Language (strict mode, ESM) |
| Turborepo | 2.8.14 | Monorepo task orchestration |
| Biome | 2.4.6 | Linter + formatter |
| Rstest | 0.9.0 | Test runner |
| Changesets | 2.30.0 | Versioning and npm publishing |
| Lefthook | 2.1.3 | Git hooks |
| Commitlint | 20.4.3 | Commit message validation |
Commands
Always run pnpm install before building or testing after a fresh clone.
pnpm install # install all dependencies
pnpm build # build all packages (via Turborepo)
pnpm test # run all tests (via Turborepo → rstest)
pnpm check-types # type-check all packages
pnpm lint # lint all packages (via Turborepo)
pnpm ci:check # Biome CI mode (lint + format, no writes)
pnpm format # auto-format everything with Biome
pnpm check # Biome check with auto-fix
To scope to a single package:
pnpm --filter mcp-a11y-color test
pnpm --filter mcp-a11y-color build
CI Pipeline
The GitHub Actions workflow (.github/workflows/ci.yml) runs on every push/PR to main:
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.
- 4d ago First seen · 156 lines · 1,531 tokens per session scan A 572d2057326d
a11y-agents-kit AGENTS.md is an instructions file published in the GitHub repository weAAAre/a11y-agents-kit (33 stars, last pushed 4mo ago), licensed MIT. It adds 1,531 tokens to every session, about $0.0077 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
core-web copilot-instructions.md
Copilot instructions for db-ux-design-system/core-web: All development instructions, build commands, validation steps, coding rules, and the pull request workflow are maintained in AGENTS.md at the repository root. Read that file first before starting any task.
wcagc-mcp CLAUDE.md
Claude Code instructions for WCAG-Compliance/wcagc-mcp, covering claude.md — wcagc-mcp, the one that bites and quick reminders (full detail in agents.md).
Copilot-Skills radix-ui.instructions.md
Automatic context for Radix UI components - provides accessibility patterns, API guidance, and best practices.
wcag-accessibility-agent CLAUDE.md
Claude Code instructions for albertomf1979/wcag-accessibility-agent, covering wcag accessibility agent — project context, what this project is, project structure, tech stack and agent behavior rules.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.