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 Rohit-ATS/Airlock --skill money-movementgit clone --depth 1 https://github.com/Rohit-ATS/AirlockWrote 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/rohit-ats/airlock/money-movement)<a href="https://agentmods.dev/skills/rohit-ats/airlock/money-movement"><img src="https://agentmods.dev/badge/skills/rohit-ats/airlock/money-movement/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/rohit-ats/airlock/money-movement"><img src="https://agentmods.dev/badge/skills/rohit-ats/airlock/money-movement.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 | $0.00041 | $0.01826 |
| Opus 5 | $0.00020 | $0.00913 |
| Sonnet 5 | $0.00008 | $0.00365 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
money-movement 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 10d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Money movement
Money that has left cannot be recalled by writing an inverse statement. There is no undo certificate for a refund, and claiming one is the single worst thing this skill exists to prevent.
A MONEY_MOVEMENT change always carries a SCOPE certificate. The claim is not "we can put it back". The claim is exactly these payments, to exactly these counterparties, for exactly this total — and explicitly not these others, for these reasons.
1. The four questions
- How much, in minor units, and in which currency? Never work in decimal majors. A float somewhere in the pipeline is how £41,904.00 becomes £41,903.99 across a thousand rows and the reconciliation fails for a week.
- To whom, counted as counterparties rather than as rows? Ten refunds to one customer is one angry phone call. One refund to ten thousand customers is a different event.
- Has any of it already gone out? This is the failure that matters. See §3.
- What is deliberately excluded, and why? The exclusion list is the part a reviewer actually reads.
2. Minor units, always
Compute, store, compare and report in the smallest unit of the currency. Convert to a display form exactly once, at the edge, for a human.
-- right
SELECT SUM(amount_minor) FROM charges WHERE ...;
-- wrong: introduces a float, and 0.1 + 0.2 is not 0.3
SELECT SUM(amount / 100.0) FROM charges WHERE ...;
Be careful with currencies that are not two-decimal. JPY and KRW have zero decimal places;
BHD, KWD and TND have three. amount_minor / 100 is wrong for five of the currencies you
are likely to meet. Read the currency, do not assume it.
Never sum across currencies to produce a single ceiling check. SUM(amount_minor) over
mixed EUR and JPY is a meaningless number that will pass a ceiling it should not.
3. Double payment — the failure that matters
The dangerous scenario is not "the refund fails". It is "the refund succeeds twice". Three defences, and use all three.
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.
- 10d ago First seen · 190 lines · 41 tokens per session scan A 9295e8e5b60c
money-movement is a skill published in the GitHub repository Rohit-ATS/Airlock (1 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,826 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
reweave-operator
Operate a Reweave self-healing web-data fleet — run pipelines, triage structural-drift incidents, review repair proposals, and manage the human approval workflow. Use whenever a monitored source is broken, a heal is pending, or the operator asks about pipeline health or impact.
economic-reasoning
Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.
financial-document-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
agent-payment-x402
A design for letting AI agents make controlled payments for APIs, services, or other agents through the x402 HTTP payment protocol and supported blockchain wallets.
portfolio
Portfolio system knowledge base. Use when: position queries, routing strategy questions, provider integration. Not for: general code exploration (use code-explore), code review (use codex-code-review). Output: domain-specific analysis + recommendations.
billing
Use for refunds, disputed charges, invoices and any billing question.