a11y-llm-eval copilot-instructions.md

a11y-llm-eval copilot-instructions.md is an instructions file for GitHub Copilot from microsoft/a11y-llm-eval. It costs 533 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on an accessibility evaluation harness. They define the project’s required behavior, including command-line options, output files, result fields, pass or fail rules, caching, and compatibility expectations.

In plain words
What is it for?
Read them before changing the CLI, evaluation logic, sampling, reports, result files, prompts, caching, or public interfaces, and update the contract and tests when behavior intentionally changes.
Why use it?
They protect existing users and tests from accidental changes to command behavior or result formats.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/microsoft/a11y-llm-eval/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/microsoft/a11y-llm-eval

Made for: GitHub Copilot.

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.

agentmods badge for a11y-llm-eval copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/microsoft/a11y-llm-eval/copilot-instructions.svg)](https://agentmods.dev/instructions/microsoft/a11y-llm-eval/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/microsoft/a11y-llm-eval/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/a11y-llm-eval/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 533 This file is loaded in full into every session.
When invoked 533 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00533 $0.00533
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 3d ago against content hash c2cb0425199f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

a11y-llm-eval 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.

.github/copilot-instructions.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions for this repository

You are working in the A11y LLM Evaluation Harness codebase.

Non-negotiable: Backwards compatibility contract

Before making any change that could affect behavior, outputs, or public interfaces, read:

  • docs/features-and-acceptance.md

Treat it as the project’s contract for:

  • CLI behavior and flags
  • run directory layout
  • results.json fields and meaning
  • evaluation pass/fail logic
  • sampling + pass@k semantics
  • prompt configuration and caching
  • Node runner I/O contract

When making changes

  1. Preserve documented behavior by default.

    • If you find a mismatch between docs and code, assume code is the source of truth and update the doc.
  2. If you intentionally change user-visible behavior (CLI, artifacts, schema, pass/fail, caching, report path/format):

    • Update docs/features-and-acceptance.md in the same PR.
    • Update or add tests in tests/ to lock the new behavior.
    • Call out breaking changes and any migration steps.
  3. Avoid accidental format drift

    • Do not rename fields in results.json without updating schema and acceptance criteria.
    • Do not change file naming conventions under runs/<id>/raw or runs/<id>/screenshots without updating docs + tests.
  4. Validation expectations

    • Prefer running the focused tests for any area you touch.
    • If you modify CLI/evaluation/reporting, run pytest.
  5. Create tests for new features

    • Add test cases under tests/test_cases/ with clear prompts and assertions.
    • Ensure new tests cover edge cases and failure modes.

Documentation hygiene

  • Keep the acceptance criteria concrete and testable.
  • Add new features to docs/features-and-acceptance.md when introduced.
  • If a behavior is deprecated, document it explicitly with the planned removal version/date.

Git workflow

  • Do not create commits unless the user explicitly asks for a commit or asks to finalize changes in git.
  • Before staging or committing, inspect git status and the relevant diffs.
  • Stage only files directly related to the requested change.
  • If unrelated local changes are present, ask before including them in a commit.
  • Use non-interactive git commands only.
  • Use commit subjects in conventional format: feat: ..., fix: ..., or chore: ....
  • Do not amend, rebase, or push unless the user explicitly asks.

Read the full file on GitHub · 58 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.

  1. 3d ago First seen · 58 lines · 533 tokens per session scan A c2cb0425199f

Subscribe to this mod's changes

a11y-llm-eval copilot-instructions.md is an instructions file published in the GitHub repository microsoft/a11y-llm-eval (59 stars, last pushed 3mo ago), licensed MIT. It adds 533 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens