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.
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 skills add microsoft/cat-agent-skills --skill edit-contractgit 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/skills/microsoft/cat-agent-skills/edit-contract)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/edit-contract"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/edit-contract/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/skills/microsoft/cat-agent-skills/edit-contract"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/edit-contract.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 | $0.00127 | $0.03090 |
| Opus 5.5 | $0.00051 | $0.01236 |
| Sonnet 5.5 | $0.00025 | $0.00618 |
| Haiku 4.5 | $0.00013 | $0.00309 |
Grade A, and why
edit-contract 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 2d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit contract
Edit an existing legal document using the smallest redline that achieves the user's instruction.
Non-negotiable tracked changes rule
Before editing the document, ensure tracked changes are enabled and used for every modification. Keep them enabled throughout the work. Do not accept or reject tracked changes unless the user explicitly asks you to do so.
When NOT to Use
- Reviewing a contract against a supplied playbook — use
review-contract. - Explaining what changed between marked-up versions — use
summarize-redlines. - Drafting a new agreement from a template or precedent — use
draft-new-contract. - Finding broken cross-references or defined term problems without editing — use
check-cross-referencesorcheck-defined-terms. - Legal advice, or deciding which position the user should take.
Hand-off rule. If a request, or part of one, matches an item above that names another skill, do
not do that part here — even when the documents are already open and the work looks quick. Name the
skill that handles it (for example, "That part is a job for review-contract") and stop that part;
finish only what belongs to this skill. If the named skill is not installed, say so plainly and do
not attempt it here.
Workflow
- Confirm the document and the requested outcome.
- Read every relevant provision, definition, cross-reference, table, heading, and surrounding passage before making changes. When opening a document, use a method that shows tracked changes and comments, and check whether any are present before relying on the text.
- Form one high-level plan for the complete requested change. Identify each target, operation, intended legal effect, placement dependency, and ordering dependency.
- Plan all requested changes to the same paragraph, clause, table, or other target together, but execute each change at the smallest text range or structural unit that can represent it without redlining unchanged content.
- Make the complete minimal set of edits in logical document order. Prefer exact insertions, deletions, and substitutions over replacement of a containing paragraph or clause. Apply independent edits together when the editing system supports it; apply dependent edits sequentially.
- Verify each edit after it is made. Preserve successful edits and correct only failed edits rather than recreating work that has already been verified.
- Review the resulting document in context, including affected definitions and cross-references, and confirm that it implements the complete request without unintended changes.
- Summarize what changed and clearly identify anything that could not be completed.
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.
- 2d ago First seen · 200 lines · 127 tokens per session scan A fe0495ecf95e
edit-contract is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 3,090 once invoked, about $0.0005 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 2026-11-06.
edit-contract compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| edit-contractmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 127 | Claude Code, Codex |
| html-ppt-zhangzara-stencil-tabletnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 49 | Claude Code, Codex |
| treatment-plansK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 62 | Claude Code, Codex |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 68 | Claude Code |
| handbook-updatesanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 52 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| software-copyright-materialsFokkyp/SoftwareCopyright-Skill | Skill | 6.3k | 16d ago | AGPL-3.0 | A | 98 | Claude Code, Codex |