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 skillgit 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/skill)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/skill"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/skill/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/skill"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/skill.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 | $0.00000 | $0.00407 |
| Opus 5.5 | $0.00000 | $0.00163 |
| Sonnet 5.5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
skill 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 2mo 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.
This is a copy
100% identical to ainumbers — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
name: ainumbers description: Deterministic regulatory-computation estate: 640+ compliance tools, chains, a verify ledger, and a timestamping anchor, callable over MCP with zero-egress in-page twins. Rules: synthetic data only; verify with verify_execution_hash before trusting; return a ledger link; never paste PII. MCP: https://mcp.ainumbers.co/mcp license: CC-BY-4.0 metadata: openclaw: requires: bins: []
AINumbers agent skill
ainumbers: the AINumbers deterministic compliance estate over MCP.
Find the right tool with find_chain / find_tool, run it, verify the artifact with verify_execution_hash before trusting any verdict, and hand back the ledger link so a human can re-verify without contacting anyone.
Rules (binding, from kit.json):
- Synthetic data only: never paste personal or production data; every tool page ships a synthetic sample and the PII banner.
- Verify before trusting: call verify_execution_hash on any artifact before relying on its verdict.
- Return a ledger link: hand back the ledger_url so a human can re-verify without contacting us.
- Never paste PII: input fields accept synthetic values only; the pages enforce zero egress, keep it that way.
Surfaces: MCP https://mcp.ainumbers.co/mcp · anchor MCP https://anchor.ainumbers.co/mcp Ledger https://ledger.ainumbers.co/ · catalog https://ainumbers.co/llms.txt
Deep links follow the fragment-only contract in kit.json (deeplink_contract): #p=v1.<base64url(gzip(JSON policy_parameters))> plus optional &run=1.
Showcase prompts: same-law-three-doorways, signed-policy-agentic-commerce, zero-egress-emir-proof, ai-marked-asset-anchored, air-gapped-helm-handover (bodies: mcp/showcase-prompts.json).
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.
- 2mo ago First seen · 32 lines · 0 tokens per session scan A 19c24e508788
skill is a skill published in the GitHub repository PostOakLabs/ainumbers (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 407 tokens. A static security scan graded it A with 0 findings. It is 100% identical to ainumbers, differing in 0 lines, and is treated as a copy.
skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skillPostOakLabs/ainumbers | Skill | 12 | today | MIT | A | 0 | Claude Code, Codex |
| risk-assessmentvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 81 | Claude Code |
| transaction-monitoringvyayasan/kyc-analyst | Skill | 61 | 4mo ago | MIT | A | 47 | Claude Code |
| sox-itgcSushegaad/Claude-Skills-Governance-Risk-and-Compliance | Skill | 1.0k | today | MIT | A | 202 | Claude Code |
| bankruptcy-monitor-qccThomasMoreAI/legal-skills-open | Skill | 99 | 25d ago | Apache-2.0 | A | 496 | Claude Code, Codex |
| leiloeiro-riscoThomasMoreAI/legal-skills-open | Skill | 99 | 25d ago | Apache-2.0 | A | 48 | Claude Code, Codex |
| recht-steuer-verfahren-momarcode1ThomasMoreAI/legal-skills-open | Skill | 99 | 25d ago | Apache-2.0 | A | 70 | Claude Code, Codex |