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 budget-and-forecastgit 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/budget-and-forecast)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/budget-and-forecast"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/budget-and-forecast/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/budget-and-forecast"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/budget-and-forecast.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 | $0.00135 | $0.03909 |
| Opus 5.5 | $0.00054 | $0.01564 |
| Sonnet 5.5 | $0.00027 | $0.00782 |
| Haiku 4.5 | $0.00014 | $0.00391 |
Grade A, and why
budget-and-forecast 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget and Forecast
Turn source actuals into a planning baseline in which every row is traceable and every unresolved item is visible.
Important: This skill assists with planning data preparation but does not provide financial advice. Budget owners and finance should review mappings, baselines, and exceptions before the planning cycle opens.
Load the accounting-root-skill skill before constructing any artifact. Its requested-file and requested-structure constraints override the example layouts below. Load the implementation skill for each requested file type before touching deliverables. Consolidate department plans without allowing a partial population, duplicate version, or dropped line to masquerade as a complete company plan.
Important: This skill assists with planning consolidation but does not provide financial advice. FP&A should review the consolidated plan and its exceptions before management use.
Create a target allocation in which every amount traces to a driver, a weight, a constraint, or a named human override.
Important: This skill assists with target-setting mechanics but does not provide financial advice and does not decide what a department's target should be. Leadership must approve, adjust, or reject the proposal.
Scope
Use this skill for the whole planning cycle: account-to-planning-line mapping, YTD-to-full-year baseline construction, period phasing, populating departmental templates and intake exceptions; the submission register, version and completeness controls, central-assumption checks and rollup by account and period; and driver selection, weighting, normalization, floors, caps, residual handling, target-versus-ask analysis and allocation governance.
Acquire and clean source actuals with whatever data connectivity and cleanup capabilities are available in the current workspace. Use financial-statements for legal-entity consolidation and intercompany eliminations. For a bridge, show each driver's contribution from the starting figure to the ending figure, and check that the contributions sum exactly to the total change. Build any leadership deck with the presentation capability available in the current workspace.
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 · 297 lines · 135 tokens per session scan A 42b255d2c32b
budget-and-forecast is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 3,909 once invoked, about $0.0005 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.
budget-and-forecast compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| budget-and-forecastmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 135 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | today | MIT | A | 39 | Claude Code, Codex |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | today | MIT | A | 28 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 4d ago | MIT | A | 110 | Claude Code |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | today | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 271 | today | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 4d ago | GPL-2.0 | A | 292 | Codex |