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 quarterly-workbackgit 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/quarterly-workback)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/quarterly-workback"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/quarterly-workback/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/quarterly-workback"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/quarterly-workback.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 | $0.00170 | $0.01896 |
| Opus 5.5 | $0.00068 | $0.00758 |
| Sonnet 5.5 | $0.00034 | $0.00379 |
| Haiku 4.5 | $0.00017 | $0.00190 |
Grade A, and why
quarterly-workback 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quarterly Work-Back Plan
Rebuilds a recurring deliverables email and its meeting series for a new cycle, using the user's own previous cycle as the template. The point is faithful replication — the format is theirs, not one this skill invents.
When NOT to Use
- Close-week status updates → use
close-status-digest - A brief for a single review meeting → use
forecast-review-prep - Executive summaries or rollups → use
exec-update - Ad-hoc or non-recurring emails → write directly
Related Skills
Hand off rather than overlap:
- Close-week status — use close-status-digest instead.
- A brief for one review meeting — use forecast-review-prep instead.
- A slide prep pack — use pptx instead.
- A written executive summary — use exec-update instead.
- Variance narrative — use variance-commentary instead.
Workflow
1. Find the prior cycle's email — this is the template
m365_search-SearchM365 with sources=["email"], from_user set to the user's own address, on
the deliverable vocabulary they use ("deliverables", "work back", "workback", "close plan", plus
their metric names). Search Sent Items across roughly the last 4-6 months.
For the matched message, fetch the full body with graph-QueryGraph selecting
subject,body,toRecipients,ccRecipients — outlook-GetMessage truncates, and these emails are
long. Working from a truncated body silently drops sections.
Extract: the complete To and Cc lists, the subject pattern, every file link, and the section structure exactly as it appears. The number and naming of sections comes from their email — do not impose a fixed outline.
If no prior email is found, ask once for recipients and file links. Never guess a recipient list.
2. Determine the cycle context
Derive the current period from today's date using the user's own fiscal convention. If their fiscal year isn't evident from the prior email's labels, ask once — a fiscal year starting in July, October, or January produces completely different quarter math, and getting it wrong makes every date in the email wrong.
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 · 167 lines · 170 tokens per session scan A d4b196fea5df
quarterly-workback is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 1,896 once invoked, about $0.0007 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.
quarterly-workback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quarterly-workbackmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 170 | 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 |