What is ainumbers AGENTS.md?

Contribution instructions for ainumbers.co, a catalogue of tools and workflows for AI agents. They explain how to propose a tool through a GitHub issue or a pull request, including the required proposal file format and repository limits.

Use them when researching ainumbers tools, suggesting a new workflow, or preparing a contribution to the repository.

They remove uncertainty about where to find the tool catalogue and how to submit a new proposal. This helps prevent pull requests from failing because they change the wrong files or use the wrong format.

ainumbers AGENTS.md — Instructions file by PostOakLabs

Install

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.

agentmods

npx agentmods add instructions/postoaklabs/ainumbers/agents-md

Clone the repo

git clone --depth 1 https://github.com/PostOakLabs/ainumbers

Made for: Codex, OpenCode.

Per session 576 This file is loaded in full into every session.

When invoked 576 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00576	$0.00576
Opus 5	$0.00288	$0.00288
Sonnet 5	$0.00115	$0.00115
Haiku 4.5	$0.00058	$0.00058

Measured 2d ago against content hash 6f9d35deb1e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ainumbers AGENTS.md 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 2d 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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Pointers for coding and browsing agents working on ainumbers.co.

MCP server card: https://ainumbers.co/mcp.html
Tool/workflow catalog for agents: https://ainumbers.co/llms.txt (extended: https://ainumbers.co/llms-full.txt)
Hash resolver (verify a receipt): https://ledger.ainumbers.co/
MCP endpoint: https://mcp.ainumbers.co/mcp

Full tool catalog, counts, and usage detail live at the links above. This file only points, it does not restate them.

Propose a new tool or workflow via PR

GitHub's account layer is the identity gate here — no separate agent verification, no tokens, no custom feed (see CONTRIBUTING.md "Moltbook doctrine" note). Two routes exist; pick the PR route for a working demonstration, the issue route for a bare idea:

Issue — https://github.com/PostOakLabs/ainumbers/issues/new?template=suggest-tool-or-chain.yml (a request; human triage reads it).
Pull request — fork, add exactly one file proposals/<kebab-slug>.json matching the schema in proposals/SCHEMA.md, open a PR. Touch nothing else — CI rejects a PR that edits anything outside proposals/. Steps:
```
gh repo fork PostOakLabs/ainumbers --clone
cd ainumbers
$EDITOR proposals/your-slug.json   # see proposals/SCHEMA.md for required fields
node scripts/verify-proposals.mjs proposals/your-slug.json   # validate locally before pushing
git checkout -b propose-your-slug
git add proposals/your-slug.json
git commit -m "propose: your-slug"
git push -u origin propose-your-slug
gh pr create --title "Propose: your-slug" --body "See proposals/your-slug.json"
```
Include a sample_artifact (a worked policy_parameters/output_payload pair with its execution_hash, computed via executionHash() in chaingraph/kernels/_hash.mjs) to earn the receipt-verified label — a working demonstration outranks a prose-only proposal in triage.

A merged proposal is not a shipped tool — it enters the normal spec → work-unit pipeline like any other build. Nothing here auto-merges or auto-builds.

Read the full file on GitHub · 47 lines

Changes

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.

2d ago First seen · 47 lines · 576 tokens per session scan A 6f9d35deb1e9

Subscribe to this mod's changes

ainumbers AGENTS.md is an instructions file published in the GitHub repository PostOakLabs/ainumbers (5 stars, last pushed 2d ago), licensed MIT. It adds 576 tokens to every session, about $0.0029 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 2026-08-31.

Deterministic compliance fintech mcp openchaingraph zero-knowledge

ainumbers AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Propose a new tool or workflow via PR

What this file has done since we first saw it

Other instructions, from other repositories

ATF-AI copilot-instructions.md

filegrc AGENTS.md

QuantRL-Lab AGENTS.md

waylMCP CLAUDE.md

aifi CLAUDE.md

banking-mcp-server CLAUDE.md