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.
git 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/commands/postoaklabs/ainumbers/ai-marked-asset-anchored)<a href="https://agentmods.dev/commands/postoaklabs/ainumbers/ai-marked-asset-anchored"><img src="https://agentmods.dev/badge/commands/postoaklabs/ainumbers/ai-marked-asset-anchored/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/commands/postoaklabs/ainumbers/ai-marked-asset-anchored"><img src="https://agentmods.dev/badge/commands/postoaklabs/ainumbers/ai-marked-asset-anchored.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 | $0.00034 | $0.00424 |
| Opus 5 | $0.00017 | $0.00212 |
| Sonnet 5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
ai-marked-asset-anchored 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 yesterday.
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
Is this asset real, AI-marked, and provably timestamped?
A marketing team is about to publish an AI-generated product image with a C2PA manifest. Decide if it can ship, and give them proof.
- On https://ainumbers.co/chaingraph/art-123-c2pa-manifest-validator.html, run the WebMCP tool with the page's synthetic manifest. Record verdict + execution_hash.
- On art-126, run check_ai_act_art50_marking with the same manifest's assertion set. On art-127, run verify_dual_layer_disclosure. Record both hashes.
- Call run_chain on content-credential-verification (art-123 > art-124 > art-125) remotely with the same synthetic manifest. Compare the art-123 step hash to your in-page hash from step 1 and state whether they are identical.
- Call build_disclosure_manifest over the five artifacts. Then call verify_disclosure_inclusion for the art-126 artifact and show the inclusion path.
- Call anchor_hash with the disclosure manifest root on OpenTimestamps. Then call upgrade_ots_proof and report whether the proof is still pending or already Bitcoin-attested (pending is expected within the first hours; say so).
- Build the ledger link for the composite chain artifact. Open it and report the §17 kernel identity and §18 compute proof lines.
- Write the publish decision: ship / do not ship, the Art. 50 findings, and a verification recipe a journalist could follow without contacting us (ledger link, OTS proof, kernel digest). 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.
Finish by stating the execution_hash you received and the ledger link a human can verify it at.
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.
- yesterday Changed · +1 lines 28a17c3790c4
- 4d ago First seen · 20 lines · 34 tokens per session scan A 154fe0f581e6
ai-marked-asset-anchored is a command published in the GitHub repository PostOakLabs/ainumbers (5 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 424 once invoked, about $0.0002 per session on Opus 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 2026-09-06.
Other commands, from other repositories
onboard
Customer onboarding with Step 0 verification (HITL consent required).
onboard-interactive
Interactive customer onboarding with Step 0 independent verification (dialog-based, 17 stagegates).
monitor
AML transaction monitoring and suspicious activity reporting.
refresh
Periodic customer review with independent verification.
risk
Risk reassessment with updated due diligence.
screen
Comprehensive sanctions and PEP screening.