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 zero-egress-emir-proofgit 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/zero-egress-emir-proof)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/zero-egress-emir-proof"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/zero-egress-emir-proof/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/zero-egress-emir-proof"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/zero-egress-emir-proof.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 | $0.00065 | $0.00779 |
| Opus 5.5 | $0.00026 | $0.00312 |
| Sonnet 5.5 | $0.00013 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
zero-egress-emir-proof 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regulatory proof without the data leaving the browser
Run four EMIR Refit validators inside the browser tab, pack and anchor only the hashes, and hand a supervisor the re-verification recipe.
Prompt
You are a trade-reporting agent at an EU counterparty. The trade report is confidential: it must not leave this machine. Prove readiness anyway.
- Take the synthetic EMIR Refit auth.030 sample from the art-158 page. Do NOT paste it into any remote call at any point.
- On each page, invoke the WebMCP-registered tool in the page with that sample:
- art-154 check_emir_uti_completeness
- art-155 validate_emir_upi
- art-157 validate_emir_lifecycle_event
- art-158 run_emir_reporting_fit Record each verdict and execution_hash. Confirm zero network requests during each call.
- Call verify_execution_hash (send the artifact or its hash as claimed_hash) on mcp.ainumbers.co for each artifact, sending ONLY the artifact (policy_parameters + output_payload as emitted by the page). State whether every recompute matches.
- Call build_evidence_pack with the four hashes, labelled by node, plus the four kernel_digest values from chaingraph.json.
- Call anchor_batch on anchor.ainumbers.co with the four hashes and the pack digest. Use two authorities: Sigstore TSA and OpenTimestamps.
- Build the ledger fragment link for the art-158 artifact and open it. Report the verify chips.
- Write the cover note for the trade repository: which checks ran, on which kernel versions, that the report content never left the workstation, and how a supervisor re-verifies with no access to us (ledger link + anchor receipt + kernel_digest). 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.
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 8664faaa025c
- 19d ago First seen · 52 lines · 65 tokens per session scan A ce508b4d942b
zero-egress-emir-proof is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 779 once invoked, about $0.0003 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.