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/same-law-three-doorways)<a href="https://agentmods.dev/commands/postoaklabs/ainumbers/same-law-three-doorways"><img src="https://agentmods.dev/badge/commands/postoaklabs/ainumbers/same-law-three-doorways.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00380 |
| Opus 5 | $0.00014 | $0.00190 |
| Sonnet 5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
same-law-three-doorways 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
Same law, three doorways
You are on an AINumbers node page. Prove that this tool gives the same answer no matter which door you use.
- List the tools this page registers via WebMCP. Note the tool name.
- Run that tool IN THE PAGE with the page's own synthetic sample (use the declared inputSchema; do not invent fields). Record the verdict and the execution_hash. Confirm the DevTools Network tab shows zero requests during the call.
- Call the SAME tool name on mcp.ainumbers.co with the identical inputs. Record its execution_hash.
- Call verify_execution_hash on the remote artifact. Then compare the two hashes character by character and state whether they are equal.
- Fetch this node's entry from https://ainumbers.co/chaingraph/chaingraph.json. Report compute_proof.system, receiptFormat, and journal.kernel_digest, and confirm the kernel_digest equals the sha256-source image_id in compute_images.
- Flip one byte in the signature field of the sample and re-run in the page. Report the new verdict and show the hash changed.
- Call build_session_receipt with the two matching hashes in call order. Record session_receipt_root.
- Call anchor_hash on anchor.ainumbers.co with session_receipt_root using the OpenTimestamps authority. Return the anchor receipt.
- Give me the ledger_url from the remote run, and a one-paragraph statement a regulator could read: which code ran (kernel_digest), where (three doorways), what it decided, and where the timestamp lives.
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 First seen · 22 lines · 28 tokens per session scan A ebb0f585c4c9
same-law-three-doorways is a command published in the GitHub repository PostOakLabs/ainumbers (5 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 380 once invoked, about $0.0001 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.