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/microsoft/a11y-llm-eval/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/a11y-llm-evalWrote 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/microsoft/a11y-llm-eval/copilot-instructions)<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>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 | $0.00533 | $0.00533 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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.
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.jsonfields and meaning- evaluation pass/fail logic
- sampling + pass@k semantics
- prompt configuration and caching
- Node runner I/O contract
When making changes
-
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.
-
If you intentionally change user-visible behavior (CLI, artifacts, schema, pass/fail, caching, report path/format):
- Update
docs/features-and-acceptance.mdin the same PR. - Update or add tests in
tests/to lock the new behavior. - Call out breaking changes and any migration steps.
- Update
-
Avoid accidental format drift
- Do not rename fields in
results.jsonwithout updating schema and acceptance criteria. - Do not change file naming conventions under
runs/<id>/raworruns/<id>/screenshotswithout updating docs + tests.
- Do not rename fields in
-
Validation expectations
- Prefer running the focused tests for any area you touch.
- If you modify CLI/evaluation/reporting, run
pytest.
-
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.
- Add test cases under
Documentation hygiene
- Keep the acceptance criteria concrete and testable.
- Add new features to
docs/features-and-acceptance.mdwhen 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 statusand 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: ..., orchore: .... - Do not amend, rebase, or push unless the user explicitly asks.
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 · 58 lines · 533 tokens per session scan A c2cb0425199f
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.
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).
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.
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.
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.
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).
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.