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 prove-compliance-reveal-nothinggit 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/prove-compliance-reveal-nothing)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/prove-compliance-reveal-nothing"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/prove-compliance-reveal-nothing/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/prove-compliance-reveal-nothing"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/prove-compliance-reveal-nothing.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 | $0.00052 | $0.00694 |
| Opus 5.5 | $0.00021 | $0.00278 |
| Sonnet 5.5 | $0.00010 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
prove-compliance-reveal-nothing 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prove compliance without revealing the transfers
Prove a transaction passes sanctions and travel-rule predicates without disclosing the transaction.
Prompt
Prove a transfer batch passes travel-rule and sanctions predicates while revealing as little as possible.
- Call validate_private_inputs to learn which fields of validate_tfr_travel_rule_batch are declared private under the §25 ocg-private-input profile. Quote the list.
- Build a synthetic 5-transfer batch. Call generate_zk_compliance_proof with predicate_type set to the travel-rule completeness predicate and the batch as private data; record the proof and the public statement. Confirm the public statement contains no originator or beneficiary fields.
- Call validate_tfr_travel_rule_batch on the same batch and confirm its verdict matches the proof's statement. Record both execution_hashes.
- Call aggregate_ownership_50pct on a synthetic ownership graph with one 50%-rule hit; then sdjwt_issue a credential asserting only "sanctions_predicate: PASS" and sdjwt_present it with every other claim withheld. Show the presentation and which claims are disclosed.
- Call validate_canton_selective_disclosure with a synthetic DvP where each party sees only its leg; confirm the attestation reconciles without either party's full view.
- Call verify_merkle_batch on the batch's audit root and one inclusion proof.
- build_session_receipt over every hash; give me the ledger link. Then list, precisely, what a verifier of that receipt learns about the underlying transfers (it should be: the predicates, the hashes, nothing else) and what they would need to trust. 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 generate_zk_compliance_proof 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.
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 6276df9fa6a3
- 19d ago First seen · 41 lines · 52 tokens per session scan A fce90e1d4aca
prove-compliance-reveal-nothing is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 694 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.