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 travel-cost-estimatorgit 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/travel-cost-estimator)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/travel-cost-estimator"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/travel-cost-estimator/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/travel-cost-estimator"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/travel-cost-estimator.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 73 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 | $0.00109 | $0.02454 |
| Opus 5 | $0.00055 | $0.01227 |
| Sonnet 5 | $0.00022 | $0.00491 |
| Haiku 4.5 | $0.00011 | $0.00245 |
Grade A, and why
travel-cost-estimator 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 8d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Travel cost estimator
Produce a defensible trip estimate from live fares and rates, not guesses, and present it so the user can forward or approve it in seconds.
The estimate has two halves. Flights and hotels come from the corporate booking tool. Ground transport, meals, and parking are not in the booking tool, so they get benchmarked against what the user has actually been reimbursed before.
HARD GUARDRAIL — read this first
The corporate booking tool is a live booking system. Real money, real tickets, real change fees, real non-refundable segments.
You are here to search and price only.
Never click: Continue past fare selection · Select hotel into a booking
funnel · Book · Reserve · Hold · Confirm · anything on a traveller-details
or payment page.
Reading fares off a results page is safe — results and the booking funnel are separate pages, and the results page is where you stop. That line is the whole guardrail.
If a flow ever lands on a page showing traveller details, payment fields, or a confirm button: stop immediately, do not click anything, and tell the user where you are. Do not try to navigate back out by clicking through.
Every estimate you produce must state "Nothing booked." explicitly.
Step 0 — establish the traveller's preferences
Before the first search, confirm (or reuse from a previous run):
| Home airport | |
| Preferred airline / alliance | |
| Preferred hotel chain | |
| Cabin class permitted by policy | |
| Trip dates and destination | |
| Rental car likely? |
Do not assume a home airport from the user's city — many metros have several, and the wrong one silently produces a plausible, useless number.
Record these preferences so later runs skip this step, but re-confirm the dates every time.
Step 1 — reach the booking tool
Use the company's SSO entry point for the booking tool (commonly a corporate shortlink or an intranet tile) so the existing session is reused.
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.
- 8d ago First seen · 260 lines · 109 tokens per session scan A c51ba1409210
travel-cost-estimator is a skill published in the GitHub repository microsoft/cat-agent-skills (67 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 2,454 once invoked, about $0.0005 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 2026-09-03.
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.