microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
Borrowing it
Nothing to install: this file belongs to microsoft/cat-agent-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.
curl -O https://raw.githubusercontent.com/microsoft/cat-agent-skills/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/microsoft/cat-agent-skillsWrote 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/cat-agent-skills/copilot-instructions)<a href="https://agentmods.dev/instructions/microsoft/cat-agent-skills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/cat-agent-skills/copilot-instructions/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.
<a href="https://agentmods.dev/instructions/microsoft/cat-agent-skills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/cat-agent-skills/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02940 | $0.02940 |
| Opus 5.5 | $0.01176 | $0.01176 |
| Sonnet 5.5 | $0.00588 | $0.00588 |
| Haiku 4.5 | $0.00294 | $0.00294 |
Grade A, and why
cat-agent-skills 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 today.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for cat-agent-skills
This repo is a gallery of reusable Agent Skills. Contributors add one
submission under submissions/<slug>/ (a metadata.json sidecar plus exactly
one payload — an unpacked SKILL.md skill, a .zip, or a Scout .json); CI
generates the published page and download bundle. See
CONTRIBUTING.md and
submissions/README.md for the full rules.
Code review rules
When reviewing a pull request, check the following in addition to CI:
The bar: block real problems, not style
These checks are a merge gate, not a copy-edit. Skills are human-authored prose and code; treat the author's wording, formatting, and structure as theirs. Only post a comment you could defend as "must fix before merge." If the worst case is "could be tidier" or "slightly inconsistent," say nothing — prefer zero comments over a nit.
Block-worthy — do raise (the rest of this section defines these):
- Executable steps, runtime dependencies, or paths that won't run on a targeted platform (see Platform fit vs. executable code).
- Human-facing prose leaking into the agent-facing
SKILL.md, or setup/adoption guidance with nowhere to live (see Human-facing vs. agent-facing content). - Submission-hygiene breaks: mixed-scope PR, hand-committed generated artifacts,
wrong file layout, invalid or renamed required
metadata.jsonfields,name/slug mismatch, or a payload that isn't aSKILL.md/.zip/ Scout.json. - Anything that breaks CI, or is a security / privacy problem (secrets, data exfiltration, harmful content).
Not block-worthy — do NOT raise:
- Writing style in the skill's own text — wording, tone, grammar, capitalization, heading style, and punctuation, including em-dashes, hyphens, and Oxford commas. A skill telling itself "no em-dashes in output" is a rule for the generated text, not for the instructions that describe it; do not flag em-dashes (or any other "banned" token) in the playbook's own prose. Raise it only if the token appears inside a literal example/template the agent emits verbatim.
- Internal-consistency and "you could also…" nits that don't change whether the skill runs or what it produces.
- Cosmetic
metadata.jsonpreferences —updatedAt/ date freshness, optional-field bikeshedding — as long as the required fields are present and valid. - Generated artifacts CI commits back (
src/content/**,public/bundles/**): never flag their presence, content, or that a PR "also changes" them — they are CI-owned, not the contributor's edit. - The same point on many lines. Make it once, in one thread; don't open a thread per occurrence.
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.
- today Changed · +8 tokens per session 461c359ea0eb
- 1mo ago First seen · 198 lines · 2,932 tokens per session scan A ab2ba279af1f
cat-agent-skills copilot-instructions.md is an instructions file published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 2,940 tokens to every session, about $0.0118 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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.