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 aml-typology-triagegit 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/aml-typology-triage)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/aml-typology-triage"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/aml-typology-triage/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/aml-typology-triage"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/aml-typology-triage.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 | $0.00047 | $0.00588 |
| Opus 5.5 | $0.00019 | $0.00235 |
| Sonnet 5.5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
aml-typology-triage 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
AML typology triage
Score transactions for AML typologies and anomalies, then seal the triage.
Prompt
Triage a synthetic alert batch and seal the reasoning trail.
- Build a synthetic batch of 50 transactions embedding three known typologies (structuring, rapid movement, round-amount pairing).
- Call score_aml_typologies. Record the typology scores; confirm the three planted typologies outrank the filler.
- Call detect_transaction_anomalies. Record the anomaly list and the method each was flagged by.
- Call simulate_app_fraud_graph over the customer-payment graph. Record the fraud clusters found and their centrality scores.
- Disagreement check: name the transactions the typology scorer and the anomaly detector disagree on; those are your review queue, not noise.
- build_evidence_pack over the scores, anomalies, and graph digests. Give me the ledger link for the pack.
- Write the triage note for the investigator: the review queue, the planted-typology recall, the pack link, and the one line that says every score recomputes from the same synthetic inputs. 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. GPU note: the score_aml_typologies tool computes in your browser, so the MCP endpoint returns no execution_hash; export the Policy Mandate artifact the page produces and pass that full artifact to verify_execution_hash as claimed_hash.
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 332d44e9c011
- 19d ago First seen · 41 lines · 47 tokens per session scan A 37b1e9f172c6
aml-typology-triage is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 588 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
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).
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.
japan-bav-und-corporate-pension-iorp
Japanisches betriebliches Altersversorgungssystem und IORP-Vergleich für europaeische Konzerne. Normen: IORP-II, japanisches Pensionsrecht DB-Pensions-Act. Prüfraster: Leistungsunterschiede, Finanzierungsanforderungen, Konvergenz. Output: Vergleichsanalyse Japan-bAV vs. EU-IORP. Abgrenzung: nicht Expatriate-Planung.
au-tax-research-ryanduguid
Use when researching an Australian tax question for a file note or draft advice: frame the question, verify each primary source and its status for the period, record alternative views and write a review-ready research file note.
regulatory-inquiry-response-bond
A Chinese-language writing assistant for responding to regulatory questions about bonds, which are debt investments issued by organisations.
steuer-at-clemensjl
Use when building or reviewing anything that issues invoices, receipts, or tax records for an Austrian business — invoice generation, receipt printing, cash register or POS integration, VAT rate tables, checkout tax logic, cross-border digital sales, accounting exports — or when asked whether an Austrian invoice or…