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 knowledge-harvestgit 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/knowledge-harvest)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/knowledge-harvest"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/knowledge-harvest/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/knowledge-harvest"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/knowledge-harvest.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 | $0.00138 | $0.01891 |
| Opus 5.5 | $0.00055 | $0.00756 |
| Sonnet 5.5 | $0.00028 | $0.00378 |
| Haiku 4.5 | $0.00014 | $0.00189 |
Grade A, and why
knowledge-harvest 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Harvest for customer service representatives
Domain: Customer Service.
Purpose
Help a customer service representative turn verified resolution evidence from a recently closed case into practical guidance for the next representative handling a similar issue. Separate the issue, cause, workaround, fix, scope, and caveats while removing customer-specific detail. The result is guidance for review and editing, not a published knowledge-base article.
Applicability
Use when evidence supports a reusable lesson from a verified resolution or an observed workaround whose scope and verification limits can be stated.
Possible overlap with existing guidance does not automatically stop the task; an update or extension may be the better disposition.
If there is no verified reusable outcome, provide only a clearly labeled evidence-gap outline and the proof needed to complete it. Do not convert unresolved speculation into executable instructions.
Data Sources
Use relevant supplied material or applicable tools and sources you are authorized to access. These are options, not a mandatory checklist. Ask for missing essential input or context; unavailable evidence remains unknown, not negative evidence.
- Resolution Notes for symptoms, investigation, attempted actions and observed outcomes.
- Verification Results for tested conditions, effectiveness and limits on generalization.
- Email for customer observations, later failures and recurrence reports.
- Meeting Transcripts for investigation decisions, scope clarifications and unresolved hypotheses.
- Internal Messaging for troubleshooting handoffs and verification caveats.
- Knowledge & Files for existing guidance, product or policy scope and overlap comparison.
- Support Records & Exports for the referenced issue's timeline, action history and affected environment.
Resolve the exact referenced context; do not assume a CRM connection. Request the missing evidence or exported case when needed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 118 lines · 138 tokens per session scan A 05e6330daf50
knowledge-harvest is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 1,891 once invoked, about $0.0006 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.
knowledge-harvest compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| knowledge-harvestmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 138 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |