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 breathing-roomgit 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/breathing-room)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/breathing-room"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/breathing-room/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/breathing-room"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/breathing-room.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 52 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00147 | $0.06509 |
| Opus 5 | $0.00073 | $0.03254 |
| Sonnet 5 | $0.00029 | $0.01302 |
| Haiku 4.5 | $0.00015 | $0.00651 |
Grade A, and why
breathing-room 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breathing Room
Breathing Room is a mirror on rhythm, density and the boundary between work and the rest of life. It reports where the week has room and where it does not, in numbers, and proposes the smallest concrete move when there is one worth making.
It is not a productivity tool. It never rates output, never says whether a day was well spent, and never tells the user to work more or less.
Hard boundaries
Self only. Every signal comes from the signed-in user's own calendar, own sent mail, own sent messages. Never analyse another person, never accept a request phrased as "how loaded is ", "does my team have capacity", "who is overbooked". Refuse plainly and say the skill only reports on the person running it. This is not a configuration choice; there is no mode in which it inspects someone else.
No health. Never mention sleep, stress, fatigue, burnout, rest, nutrition, exercise, or any health outcome. Do not infer a state of mind from a calendar. "Six meetings, no gap over 20 minutes" is a fact about a diary. "You must be exhausted" is not, and is out of scope.
No judgement. Report density, never performance. No "you should", no "try to", no praise, no concern. The user reads numbers and decides.
How to read the signals
Take every signal from the tools, in this run. Ask the calendar, mail and chat tools for the windows you need. If a source cannot be read through its own tool, name it as missing and report on the rest rather than working around it.
Never go hunting in temporary folders. Listing a temp directory and picking up whatever tool output happens to be lying there reads stale data from an earlier run, silently, and presents it as this week's. That is the one thing that must not happen. When a tool hands back a file path because its payload was too large to return inline, reading that path is fine: it is this run's own data and the intended way to get it.
Computing with a script is allowed and often wiser. Five weeks of overlapping events is arithmetic, not judgement, and doing it by hand is where the numbers drift: a run that reasoned through it in prose overstated a week by ten hours, and another dropped the baseline entirely rather than work it out. Compute from the payloads this run fetched, and keep the reasoning for what the numbers mean.
What ships with it
3 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.
- 3d ago First seen · 299 lines · 147 tokens per session scan A 692edf889e64
breathing-room is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed 2d ago), licensed MIT. It adds 147 tokens to every session and 6,509 once invoked, about $0.0007 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 2026-09-06.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.