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/copilot-instructionsgit clone --depth 1 https://github.com/mgifford/ACCESSIBILITY.mdWrote 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/mgifford/accessibility.md/copilot-instructions)<a href="https://agentmods.dev/instructions/mgifford/accessibility.md/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mgifford/accessibility.md/copilot-instructions.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 | $0.00549 | $0.00549 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
ACCESSIBILITY.md copilot-instructions.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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Repository Instructions
Purpose and Usefulness
This file is a compatibility entry point for GitHub Copilot. The canonical, tool-neutral repository instructions are in AGENTS.md.
This file is useful because some GitHub Copilot surfaces load
.github/copilot-instructions.md but do not automatically load AGENTS.md. It
is not a second repository policy and must not repeat the content of
AGENTS.md. See GitHub's current
custom-instruction support matrix.
If the repository stops using GitHub Copilot, this file can be removed without moving its contents elsewhere.
Required Behavior
- Read and follow AGENTS.md. It defines repository scope,
authority, workflow, validation, and completion requirements, including how
to find a more specific
AGENTS.md. - Treat this file, applicable
AGENTS.mdfiles, and applicable path-specific instruction files as one instruction set. Report a material conflict rather than guessing. - If the current Copilot surface cannot read
AGENTS.md, report that the canonical repository instructions are unavailable instead of substituting rules from this file.
Copilot-Specific Notes
- GitHub Copilot features and editors do not all support the same instruction
file types. When the interface exposes loaded references or instructions,
confirm that the applicable
AGENTS.mdwas loaded. If it was not, add it to the context or report that the canonical instructions may not have applied. - Copilot code review uses instructions from the pull request's base branch. Changes to instruction files in the pull request itself should not be expected to affect that review.
- Examples involving Copilot actions, agents, models, or preview features can become outdated. Verify current behavior in official GitHub Copilot documentation before recommending, copying, or enabling them.
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 · 55 lines · 549 tokens per session scan A 739e3abcd1a9
ACCESSIBILITY.md copilot-instructions.md is an instructions file published in the GitHub repository mgifford/ACCESSIBILITY.md (71 stars, last pushed 7d ago), licensed MIT. It adds 549 tokens to every session, about $0.0027 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.
arena AGENTS.md
AGENTS.md instructions for dravensoft-dev/arena, covering arena, for whoever changes it, which job is this?, where each decision goes, what this repo ships and where a new document goes.