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 PostOakLabs/ainumbers --skill verify-a-receipt-someone-sent-megit clone --depth 1 https://github.com/PostOakLabs/ainumbersWrote 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/postoaklabs/ainumbers/verify-a-receipt-someone-sent-me)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/verify-a-receipt-someone-sent-me"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/verify-a-receipt-someone-sent-me/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/postoaklabs/ainumbers/verify-a-receipt-someone-sent-me"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/verify-a-receipt-someone-sent-me.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 | $0.00056 | $0.00512 |
| Opus 5.5 | $0.00022 | $0.00205 |
| Sonnet 5.5 | $0.00011 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
verify-a-receipt-someone-sent-me 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 15d 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.
What it actually says
Verify a receipt someone sent me
I was sent a receipt link. Check it is real and see exactly what ran, without trusting the sender.
Prompt
You were handed a receipt link. Check it from primary sources before you rely on it.
- Open the receipt link. Copy its execution_hash and the named chain and step.
- Call find_chain for the chain named in the receipt; note the node and tool that produced the step.
- Re-run the same step yourself with run_chain using the receipt's recorded input_payload (or the tool's declared synthetic sample if inputs are not in the receipt).
- Call verify_execution_hash over your run's {policy_parameters, output_payload} and compare with the receipt's execution_hash, character by character.
- State which fields would have to change for the hash to differ, and which fields are not covered by the hash.
- build_session_receipt over your re-check and give me the ledger link for it.
- Write a three-line verdict for whoever sent you the link: reproduced / not reproduced, what matched, and the ledger link. If a named tool is not in your tool list, call call_tool with { "name": "", "arguments": { … } }. It runs the same validation and returns the same receipt.
How to run
Connect an MCP-capable host to https://mcp.ainumbers.co/mcp, then give the prompt above to the assistant.
Use synthetic inputs only. Never paste personal or production data.
Verify what came back
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.
- 15d ago Changed 1a0983d43dfc
- 19d ago First seen · 39 lines · 56 tokens per session scan A badccc012b82
verify-a-receipt-someone-sent-me is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 512 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
gdpr-dsgvo-expert-neekware
GDPR and German DSGVO compliance automation. Scans codebases for privacy risks, generates DPIA documentation, tracks data subject rights requests. Use for GDPR compliance assessments, privacy audits, data protection planning, DPIA generation, and data subject rights management.
lint
Health-check the vault's wiki (Axis 1): report where it bleeds — dangling [[links]], orphan notes nobody links to, stale entity pages left behind by fresher notes, and malformed frontmatter. Runs a deterministic scanner and reads its binary report, then acts, announces or asks depending on the gesture (ADR 0043's…
openclaw-tune
OpenClaw system-level maintenance — cleans sessions/.bak rotation, disk bloat under /.openclaw/, validates model fallback chain, audits cron health, prunes short-term-recall noise. Run after openclaw update or every 1-2 weeks. Different from workspace document tune-up (single-responsibility canonical .md files, token…
ai-sre-incident-response
Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.
implement
Implement a feature or fix with automatic validation.
error-handling
Validate error handling completeness across languages.