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 redlining-contentgit 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/redlining-content)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/redlining-content"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/redlining-content.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.01143 |
| Opus 5 | $0.00042 | $0.00571 |
| Sonnet 5 | $0.00017 | $0.00229 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
redlining-content 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redlining Content Skill
Reimplements "Word Compare" for the new Copilot Studio orchestrator. The
template is already a perfect Word document, so the output is the template
body with revisions injected as OOXML <w:ins> / <w:del> elements. Accepting
all changes yields the submission's wording; rejecting all keeps the template.
Changes are authored by Copilot Studio AI and the output has Track
Changes turned on so Word keeps tracking any further human edits.
Requirements
lxml(always)pdfplumber(PDF submissions;pypdfium2used as a fallback)
All are present in the Copilot Studio sandbox — no pip install required.
.docx/.dotx handling is pure lxml + standard library.
Inputs
- Template — the canonical baseline. Bundled with this skill in
assets/(any single.dotx/.docxfile — the name doesn't matter) and used automatically. A different template (.dotxor.docx) may be supplied explicitly to override it. - Submission — the user-uploaded file to compare against the template,
either a
.docxor a.pdf.
Steps
- Run from this skill's directory:
python scripts/redline.py <submission.docx|.pdf> [output.docx]The bundled template inassets/is auto-discovered and used as the baseline (whatever its file name). To override the template explicitly, pass it via--template:python scripts/redline.py --template <template.dotx|.docx> <submission.docx|.pdf> [output.docx] - Return the output
.docxto the user. Output defaults to the submission name with a_redlined.docxsuffix.
How it works
One shared engine, two input readers — the only thing that differs by file type is how the submission's words are read:
.docx/.dotx→read_docx_words()(paragraph text fromword/document.xml)..pdf→read_pdf_words()(text extraction only — never converted to DOCX; uses pdfplumber, then pypdfium2).
Both produce a single flat word list fed into the same pipeline:
What ships with it
5 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 · 94 lines · 84 tokens per session scan A 4bb1e2599430
redlining-content is a skill published in the GitHub repository microsoft/cat-agent-skills (64 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,143 once invoked, about $0.0004 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
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
software-certificate-skill
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.