What is a11y-specialist-skills AGENTS.md?

Writing and development instructions for a repository of accessibility skills and guides. Accessibility means making software usable by people with different disabilities and interaction needs.

They help write actionable review guidance, specify report formats and severity levels, identify cases needing manual checks, and maintain localized documentation.

They keep the documents focused on applying existing accessibility knowledge instead of repeating basic standards. They also define how English and Japanese versions should stay aligned.

How masuP9/a11y-specialist-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to masuP9/a11y-specialist-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/masuP9/a11y-specialist-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/masuP9/a11y-specialist-skills

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/masup9/a11y-specialist-skills/agents-md/github.svg)](https://agentmods.dev/instructions/masup9/a11y-specialist-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/masup9/a11y-specialist-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/masup9/a11y-specialist-skills/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/masup9/a11y-specialist-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/masup9/a11y-specialist-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 751 This file is loaded in full into every session.

When invoked 751 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00751	$0.00751
Opus 5.5	$0.00300	$0.00300
Sonnet 5.5	$0.00150	$0.00150
Haiku 4.5	$0.00075	$0.00075

Measured 24d ago against content hash 61b2f6e2a194, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

a11y-specialist-skills 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 24d 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.

AGENTS.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Guidelines

Writing Skills and Guides

Assume the Agent's Prior Knowledge

Claude Code and Codex already know accessibility standards thoroughly. Do not include:

WCAG 2.x success criteria definitions
WAI-ARIA roles, states, and properties
Basic HTML semantics
General accessibility principles

Instead, focus on:

How to apply the knowledge (review process, tool usage)
What to output (report format, severity criteria)
When to flag issues for manual verification
Project-specific conventions

Keep It Actionable

Write instructions, not tutorials
Use tables and lists for quick reference
Include concrete examples of expected output

Localization

This project maintains documentation in both English and Japanese.

File Naming Convention

English (default)	Japanese
`SKILL.md`	`SKILL.ja.md`
`README.md`	`README.ja.md`
`references/*.md`	`references/*.ja.md`

Sync Rules

Always keep English and Japanese versions in sync
Japanese (.ja.md) files are the source of truth for content
English files are translations of the Japanese source
When updating content, update the Japanese version first, then sync to English
When adding a new file, create both language versions

Shared Skill Compatibility

Keep one shared SKILL.md for Claude Code and Codex; do not duplicate platform-specific skill bodies.
Preserve argument-hint and allowed-tools in skill frontmatter. Claude Code uses them, and the supported Codex runtime tolerates these extensions.
Validate skills with npm run validate:skills. The upstream Codex quick_validate.py is not the compatibility gate because it rejects the Claude Code argument-hint extension.
Express workflow steps in terms of capabilities instead of platform-specific tool names.
Put Codex presentation metadata in agents/openai.yaml, not in a second skill file.
Keep the version synchronized across .claude-plugin/plugin.json, both version fields in .claude-plugin/marketplace.json, and .codex-plugin/plugin.json.

Read the full file on GitHub · 78 lines

Changes

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.

24d ago Changed · +11 lines · +242 tokens per session 61b2f6e2a194
2mo ago First seen · 67 lines · 509 tokens per session scan A 5245c9d82a15

Subscribe to this mod's changes

a11y-specialist-skills AGENTS.md is an instructions file published in the GitHub repository masuP9/a11y-specialist-skills (61 stars, last pushed today), licensed MIT. It adds 751 tokens to every session, about $0.0030 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 2026-08-30.

Design and UX

a11y-specialist-skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
a11y-specialist-skills AGENTS.mdmasuP9/a11y-specialist-skills	Instructions file	61	today	MIT	A	751	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

a11y-specialist-skills: Instructions file for Codex