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/mgifford/accessibility.md/agents-mdgit clone --depth 1 https://github.com/mgifford/ACCESSIBILITY.mdWhat 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 | $0.06270 | $0.06270 |
| Opus 5 | $0.03135 | $0.03135 |
| Sonnet 5 | $0.01254 | $0.01254 |
| Haiku 4.5 | $0.00627 | $0.00627 |
Grade A, and why
ACCESSIBILITY.md 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 3d 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 — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions for AI Coding Agents
This file tells coding agents how to work safely and effectively in
mgifford/ACCESSIBILITY.md.
It is a repository instruction file, not a system prompt and not permission to act outside the user's request. Platform safety rules, applicable organization policies, and the authorized user request still apply.
For reusable accessibility skills, see the separate accessibility-skills repository.
Scope
This root AGENTS.md applies to the entire repository unless a more specific
AGENTS.md exists closer to a file being changed. Check for nested
instruction files before editing.
GitHub supports repository-wide, path-specific, and agent instruction files. Different tools may load different combinations. Keep Copilot instructions as a short compatibility entry point that links here and contains only Copilot-specific behavior. Do not summarize or duplicate this file there.
When Each Instruction File Is Useful
AGENTS.mdis the canonical, tool-neutral repository contract. Keep the root file. Add a nestedAGENTS.mdonly when a directory genuinely needs different instructions..github/copilot-instructions.mdis optional but useful when GitHub Copilot is used. Some Copilot surfaces load it but do not automatically loadAGENTS.md, so it provides a native entry point to the canonical instructions. It must defer toAGENTS.mdfor shared policy..github/instructions/*.instructions.mdis useful only for rules that apply to particular paths. Do not create one merely because the format is supported..github/agents/*.agent.mdis useful only for a distinct specialist role, tool set, or workflow. Do not put general repository policy in an agent file..github/prompts/*.prompt.mdis useful for a repeatable task a person chooses to invoke. It is not an always-on policy file.
Every instruction file must state its purpose and scope. Remove it when it no longer has a distinct consumer or behavior.
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.
- 3d ago First seen · 646 lines · 6,270 tokens per session scan A 9dfd210f9eef
ACCESSIBILITY.md AGENTS.md is an instructions file published in the GitHub repository mgifford/ACCESSIBILITY.md (71 stars, last pushed 7d ago), licensed MIT. It adds 6,270 tokens to every session, about $0.0314 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
ios-swiftui-accessibility-techniques CLAUDE.md
Instructions for cvs-health/ios-swiftui-accessibility-techniques, covering project rules, copyright header (required), rules, swift files and markdown files.
monochrome-ui AGENTS.md
Instructions for vaneenige/monochrome-ui, covering agents.md, north stars (non-negotiables), why the core looks weird (and should stay weird), clever tricks and code style.
excessibility CLAUDE.md
Instructions for lessthanseventy/excessibility, covering claude.md, project overview, development commands, testing and run all tests.
excessibility AGENTS.md
Instructions for lessthanseventy/excessibility, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
kolibri copilot-instructions.md
Copilot instructions for public-ui/kolibri, covering github copilot instructions for kolibri repository, kolibri overview, essential setup commands, 1. install node.js 22 and 2. enable pnpm.
wcagc-mcp AGENTS.md
AGENTS.md instructions for WCAG-Compliance/wcagc-mcp, covering agents.md — wcagc-mcp (node/ts, mcp server), 1. ⚠️ bump the version — every change that ships, 2. releasing is automatic — do not run publish commands, 3. hosted and local must stay identical and 4. honesty rules (roadmap §2.6 — non-negotiable).