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 agent-audit-trail-for-the-examinergit 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/agent-audit-trail-for-the-examiner)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/agent-audit-trail-for-the-examiner"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/agent-audit-trail-for-the-examiner/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/agent-audit-trail-for-the-examiner"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/agent-audit-trail-for-the-examiner.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 | $0.00058 | $0.00583 |
| Opus 5.5 | $0.00023 | $0.00233 |
| Sonnet 5.5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
agent-audit-trail-for-the-examiner 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
Agent audit trail for the examiner
Aggregate every receipt from today’s agent session into one audit object a regulator can re-verify.
Prompt
One audit object for a day of agent activity, framed the way an examiner asks.
- Collect today's execution receipts (ids and hashes) from your agent sessions. Synthetic sessions are fine; the mechanics are what you are proving.
- Call aggregate_execution_receipts over the set. Record the aggregate digest and any receipt it could not include, with the reason.
- Call build_session_receipt over the aggregate. This is the Art. 12-style log entry: what ran, when, under which hash.
- Call compose_ap2_prompt to render the regulator-framed summary of the aggregate. Record the prompt text it returns.
- Completeness test: remove one receipt id from the set, re-aggregate, confirm the digest changes. Quote both digests; that sensitivity is what makes the aggregate meaningful.
- anchor_stamp the aggregate digest on OpenTimestamps.
- Give me the ledger link and the OTS receipt.
- Write the examiner note: session coverage window, receipt count, the aggregate digest, both receipts, and the one line stating the log recomputes from the receipts, not from your records. Call shape: every ChainGraph node tool takes its arguments nested under one wrapper object, e.g. {"policy_parameters": { ... }}; flat arguments are discarded by schema validation. 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 903c12c088b3
- 19d ago First seen · 41 lines · 58 tokens per session scan A 9e8dc82e1225
agent-audit-trail-for-the-examiner is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 583 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
fsi-compliance-checker
Maps code, architecture, and infrastructure changes to specific control IDs in PCI-DSS v4.0 and MAS TRM (Singapore financial regulator), producing an audit-traceable findings report with per-control remediation.
onboarding
Full KYC customer onboarding with mandatory Step 0 independent verification (5+1 searches), 17 sequential stagegates requiring explicit analyst consent, deterministic four-factor risk scoring, case folder auto-creation, 4-sheet Excel dashboard, 17-section PDF report, and immutable audit trail. Covers UK/EU (AMLD5), US…
risk-assessment
Deterministic heuristic risk scoring using a four-factor weighted model (Geographic 30%, Customer 35%, Product 25%, Channel 10%) aligned with Basel III, EBA Guidelines, FATF standards, and FinCEN guidance. Bands: LOW (0-20), MEDIUM (21-60), HIGH (61-80), CRITICAL (81-100).
screening
Comprehensive sanctions and PEP screening against 12+ databases (OFAC, EU, UK, UN, INTERPOL) with false positive assessment, HITL decision gates, and regulatory-compliant documentation.
refresh
Periodic customer refresh with re-verification of original due diligence to detect material changes and maintain compliance with ongoing due diligence requirements. Triggers include time-based review (annual HIGH risk, 2-3 year intervals for MEDIUM/LOW), risk-based escalation (score changes, business pivots), and…
transaction-monitoring
AML transaction monitoring for ongoing customer relationships. Identifies suspicious patterns including structuring, layering, and unusual activity. Assesses against regulatory thresholds and prepares Suspicious Activity Reports (SARs) with HITL decision gates.