openai-cookbook is a collection of example code and practical guides for completing common tasks with the OpenAI API. It is for developers building applications that call OpenAI models, with most examples written in Python. The catalogue add-ons provide reusable workflows for working with the cookbook and OpenAI API examples.
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 openai/openai-cookbook --skill expense-review-policygit clone --depth 1 https://github.com/openai/openai-cookbookWrote 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/openai/openai-cookbook/expense-review-policy)<a href="https://agentmods.dev/skills/openai/openai-cookbook/expense-review-policy"><img src="https://agentmods.dev/badge/skills/openai/openai-cookbook/expense-review-policy/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/openai/openai-cookbook/expense-review-policy"><img src="https://agentmods.dev/badge/skills/openai/openai-cookbook/expense-review-policy.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 | $0.00017 | $0.00570 |
| Opus 5.5 | $0.00007 | $0.00228 |
| Sonnet 5.5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
expense-review-policy 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expense review policy
Policy ID: AP-104.
Apply this policy to invoices, expense receipts, and service contracts.
Invoices and expenses
- Read the entire invoice, including the vendor and every line item.
- Extract every line item's quantity and unit price before calculating. Check the extracted list against every source line; an empty list is an error, not a zero subtotal.
- Use Python's
decimal.Decimalto multiply quantities by unit prices and sum the line totals. Compare this subtotal with the printed subtotal, then add shipping to calculate the total. - Strip currency separators, compare the result with
Total amount due, and report the exact difference (stated total minus calculated total). - Require a purchase order or another documented approval.
- Flag missing receipts, unsupported charges, and changed payment instructions.
- Escalate incorrect totals and unverified changes to bank details.
Contracts
- Read every clause and report all matching risks, even when one already requires escalation.
- Flag automatic renewals and restrictive cancellation windows.
- Flag unilateral price increases and missing liability limits.
- Escalate customer-data sharing or subcontractor access without approval.
- Identify missing confidentiality, security, or termination terms.
Review decision
needs_info: Required documentation or supporting information is missing.escalated: Fraud indicators, financial discrepancies, or risky terms need review.ready_for_approval: No policy violations remain, but a human must still approve.
Write /workspace/output/<document-stem>.json with the following fields:
{
"document": "invoice.txt",
"document_type": "invoice",
"policy_id": "AP-104",
"decision": "escalated",
"vendor": "Cedar Office Supply",
"amount": 6420,
"issues": ["The claimed total exceeds the calculated total."],
"recommendation": "Escalate for human review.",
"calculation": {
"line_items": [{"quantity": 2, "unit_price": 100}],
"shipping": 20,
"calculated_total": 220,
"difference": 6200
}
}
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 Changed · +13 lines 116ff3d1b82e
- 1mo ago First seen · 52 lines · 17 tokens per session scan A 33f3b498db9f
expense-review-policy is a skill published in the GitHub repository openai/openai-cookbook (76,829 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 570 once invoked, about $0.0001 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 2026-09-11.
Other skills, from other repositories
kyc-escalation
Write an internal KYC/AML escalation memo: a factual time-stamped trigger description, customer-profile vs activity mismatch analysis, red-flag taxonomy mapping, outstanding information, and a recommendation with rationale. Use when asked to escalate a KYC alert, document an AML concern, write up unusual-activity…
nl-tax-box3
Use when an owning Dutch tax workflow needs Box 3 facts and questions; annual 2025 compares fictitious and actual return, while provisional 2026 uses the fictitious method only.
nl-tax-box1-home
Use when an owning Dutch tax workflow needs sourced Box 1 or own-home facts and questions; use annual 2025 evidence for annual workpacks and labeled 2026 estimates for provisional workpacks.
nl-tax-box2
Use when an owning Dutch tax workflow needs standard Box 2 facts and questions; use reviewed 2025 amounts for annual workpacks and labeled 2026 estimates or baseline amounts for provisional workpacks.
nl-tax-partner-deductions
Use when an owning Dutch tax workflow needs fiscal-partner, deduction, or allocation facts and review scenarios for annual 2025 or provisional 2026 preparation.
nl-tax-provisional-assessment
Use when the user explicitly wants a 2026 Dutch provisional request, change, review, or stopzetten workpack. Changes require complete-data re-entry before questions; Box 3 is fictitious-only.