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 nightly-receipt-tamper-checkgit 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/nightly-receipt-tamper-check)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/nightly-receipt-tamper-check"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/nightly-receipt-tamper-check/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/nightly-receipt-tamper-check"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/nightly-receipt-tamper-check.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 | $0.00060 | $0.00523 |
| Opus 5.5 | $0.00024 | $0.00209 |
| Sonnet 5.5 | $0.00012 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
nightly-receipt-tamper-check 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
Nightly receipt tamper check
Every night, re-verify every receipt in my export and tell me exactly what changed, if anything.
Prompt
Set up the nightly habit: re-verify every receipt in your export and surface any drift.
- Export your receipts from the ledger page to receipts.json (id, chain, step, execution_hash, input_payload per line).
- For each receipt, call find_chain to resolve the node and tool that produced it.
- Re-run each step with run_chain using the recorded input_payload. Record today's execution_hash next to the stored one.
- Call verify_execution_hash on each pair and classify: MATCH, MISMATCH, or UNRUNNABLE (input no longer accepted).
- For every MISMATCH, diff the stored input_payload against today's accepted schema and quote the differing field.
- build_session_receipt over the whole sweep. Give me the ledger link.
- Write the nightly note for your own channel: counts per class, any MISMATCH with its diff, and the ledger link. Save the note where your cron already posts, so tomorrow's run compares against today's counts. 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 79a584bc00ba
- 19d ago First seen · 39 lines · 60 tokens per session scan A df088314cf4f
nightly-receipt-tamper-check is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 523 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
leave-tracker-zhou210712
A tracker for ongoing employee leave cases with legally important deadlines. It focuses on leave that needs a decision or action, such as medical leave, maternity leave, annual leave, or work-injury leave.
cold-start-interview-ria-sistemas
Entrevista inicial do advogado pra popular o practice profile (CLAUDE.md) do plugin previdenciario-legal-br. Roda na primeira execucao do plugin, captura identidade OAB, JEF/TRF predominante, foco de atuacao (previdenciario puro, acidentario, assistencial), tipos de beneficio mais frequentes, perfil de cliente tipico…
preparacao-de-ato-eletronico-sbroggioadv
Esta skill deve ser usada quando o advogado pedir preparação de participação no e-Notariado, escritura familiar eletrônica ou híbrida, videoconferência, assinatura digital ou conferência de competência remota. Produz mapa de dependências sem lavrar ou operar a plataforma pela serventia.
hr-people-operations
Help HR managers, People Ops specialists, HRIS administrators, and HR generalists understand, design, and run core people operations processes. Use when asked to design an onboarding workflow, set up an HRIS, build an offboarding checklist, create an employee handbook, audit HR data quality, design a people ops…
hr-hris
Help HR managers, HR operations teams, and recruiters understand HRIS (Human Resource Information Systems), including HRIS platforms, implementation and migration, system integrations, employee data management, HR automation, and HRIS-related hiring. Use when asked to explain HRIS, choose an HRIS platform, implement…
hr-onboarding
Help HR managers with employee onboarding and offboarding. Use when asked to create an onboarding plan, design orientation programs, build a buddy system, write onboarding checklists, conduct exit interviews, manage knowledge transfer, create offboarding processes, or any employee onboarding or offboarding task.