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 reconciliationgit 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/reconciliation)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/reconciliation"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/reconciliation/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/reconciliation"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/reconciliation.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 | $0.00138 | $0.08000 |
| Opus 5.5 | $0.00055 | $0.03200 |
| Sonnet 5.5 | $0.00028 | $0.01600 |
| Haiku 4.5 | $0.00014 | $0.00800 |
Grade A, and why
reconciliation 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconciliation
Important: This skill assists with reconciliation workflows but does not provide financial advice. All reconciliations should be reviewed by qualified financial professionals before sign-off.
Methodology and best practices for account reconciliation, including GL-to-subledger, bank reconciliations, and intercompany. Covers reconciling item categorization, aging analysis, escalation, and the deliverables that package reconciliation work: reconciliation memos, vendor correspondence, AP discrepancy trackers, and supervisor review packs.
Read Reconciliation Standards before you build — the cross-cutting output discipline, applied as checks on your own work (not a template): reconcile within the account's materiality threshold and show the computed difference (tight for cash/bank, looser for estimate-heavy accounts like accruals — it need not be exactly $0); tie support to the official GL / trial-balance figure that ties to the ERP, and show the difference; use live formulas, never hardcoded balances; cover the complete population; label each material figure disclosed-vs-derived with its source and period, and never present a guess as disclosed; document the inputs, methodology, exceptions above threshold, and a definitive conclusion — cross-tie related accounts for reasonableness (e.g., AR vs revenue given the payment terms) and propose the most-likely cause of each exception; and never guess silently — state the assumption you took wherever the inputs left a choice open. Apply the treatment the task calls for and don't impose structure it doesn't need; the sections below add the type-specific mechanics.
Structure precedence — apply before the methodology
The user's requested deliverable structure and any supplied template are authoritative. The formats below are examples of content, not required tabs or layouts.
- Preserve exact tab count, names, order, template rows/columns, headers, and formulas when specified. Do not insert a cover, README, requirements checklist, controls sheet, source index, copied source-data tab, memo, reviewer-notes tab, or exception tab unless explicitly requested or already present in the template.
- Keep the requirements checklist and detailed analysis in working notes. Put only requested output into the workbook.
- "Audit-ready," "controller-ready," "professional," and "reusable" never expand scope. Achieve those qualities with formulas, labels, and concise notes inside the requested tabs.
- If the request says "only," "exactly," "do not add/rename/delete/reorder," or "template exactly as supplied," treat that as a hard failure boundary. Do not apply a standard format that conflicts with it.
- When no layout is prescribed, choose the smallest structure that fully satisfies the request. Add a separate schedule or memo only when its content cannot fit clearly in an already-required tab and the user has not limited the structure.
What ships with it
1 file 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.
- 2d ago First seen · 517 lines · 138 tokens per session scan A 7feeb26f715e
reconciliation is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 8,000 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 2026-11-06.
reconciliation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reconciliationmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 138 | 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 |