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 institutional-knowledgegit 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/institutional-knowledge)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/institutional-knowledge"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/institutional-knowledge/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/institutional-knowledge"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/institutional-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Data Exfiltration · line 336 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00143 | $0.06043 |
| Opus 5.5 | $0.00057 | $0.02417 |
| Sonnet 5.5 | $0.00029 | $0.01209 |
| Haiku 4.5 | $0.00014 | $0.00604 |
Grade A, and why
institutional-knowledge 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 1mo 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 — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/institutional-knowledge — Executive Knowledge Preservation
Intent. Build a comprehensive, structured knowledge archive of a senior leader's tenure by mining their Microsoft 365 signals (emails, Teams chats, meetings, OneDrive/SharePoint contributions), distilling decisions/rationale/relationships, and producing a multi-phase document a successor or AI assistant can ground on. Designed for long-tenure senior leaders (3+ years) whose departure would otherwise lose significant decision history and tribal knowledge.
This skill is resumable. Each invocation reads manifest.md and continues where the last session stopped. Plan for a 1-week sprint across multiple sessions.
0. Core operating principles
- The leader curates; you produce. The user (the departing leader, or a delegate working with them) answers clarifying questions and validates. You write everything.
- Decision archaeology is the highest-value output. Bias toward capturing why decisions were made over what projects exist. Successors can read project trackers; they can't recover lost rationale.
- Multi-phase, gated progression. Phase 1 (discovery) → Phase 2 (deep extraction) → Phase 3 (cross-cutting themes) → Phase 4 (gap questionnaire) → Phase 5 (final assembly). Confirm with the user before advancing phases.
- Idempotent ingest. Every signal is keyed by
(source_id, item_id)or(source_id, date). Re-running merges, never duplicates. - Capture before polish. Get raw signals down across all phases before refining. If time runs short, raw breadth beats polished narrowness.
- Privacy. The archive is built from private signals and lives on the user's machine inside their M365 trust boundary. HR / compensation / performance / health content is automatically out of scope. The leader alone decides what to share with the org or successor.
1. First-run bootstrap
Default archive path: $env:USERPROFILE\Documents\institutional-knowledge on Windows/PowerShell hosts, ~/Documents/institutional-knowledge elsewhere. Some Cowork/Scout sandboxes expose a different writable root and may not set $env:USERPROFILE — if the default path can't be resolved or written, discover a writable Documents/-equivalent folder from the host and confirm it with the user before scaffolding. Detection: an AGENTS.md containing the marker institutional-knowledge-schema-v1 in its first 200 chars (written during scaffold — see §1.4).
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.
- 1mo ago First seen · 528 lines · 143 tokens per session scan A 943b4e851a9c
institutional-knowledge is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 143 tokens to every session and 6,043 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 2026-08-30.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…