Borrowing it
Nothing to install: this file belongs to PostOakLabs/ainumbers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PostOakLabs/ainumbers/main/CLAUDE.mdgit 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/instructions/postoaklabs/ainumbers/claude-md)<a href="https://agentmods.dev/instructions/postoaklabs/ainumbers/claude-md"><img src="https://agentmods.dev/badge/instructions/postoaklabs/ainumbers/claude-md/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/instructions/postoaklabs/ainumbers/claude-md"><img src="https://agentmods.dev/badge/instructions/postoaklabs/ainumbers/claude-md.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 | $0.01384 | $0.01384 |
| Opus 5.5 | $0.00554 | $0.00554 |
| Sonnet 5.5 | $0.00277 | $0.00277 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
ainumbers CLAUDE.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 3d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — repo/ Build Directive
Scoped to the deployable code in this folder. For workspace layout, git workflow, and project context read
../CLAUDE.mdfirst.
Role: Deterministic, privacy-first fintech web engineer.
SSOT: CONTRACT.md - read §0–§6 before generating, modifying, or validating any file, plus the annex your row class names (map below). Amendments and appendices are read on demand, never skipped when named.
- tool page rows → §1, §3, §4, §6
- guide/hub rows → §1, §5, §6.3
- kernel / node-shard rows → §6, A3, A4 + the
execution_hashrule below - MCP worker / manifest rows → §2, A4
- chain rows → A3
- claim-register or evidence rows → A14, §15
Moved out (load on demand): build workflow, wave completion checklist and scale commands → skill wave-checklist (.claude/skills/wave-checklist/SKILL.md). Tool-HTML-only rules (lang toggle, Policy Mandate export, export tiers, PII banner) → .claude/rules/tool-html.md (loads when tools/**/*.html is touched).
Layout: tools/ (standalone tool HTML), guides/ (*-hub.html), manifests/ (one per tool), chaingraph/, index.html, CONTRACT.md. Canonical templates: tools/152-baas-provider-comparator.html, manifests/01-a2a-fee-route-optimizer.manifest.json.
🔒 Non-Negotiable Constraints
- Single self-contained
.htmlper tool. Inline CSS/JS only. Google Fonts (DM Serif Display,Sora,JetBrains Mono) only. - Zero network calls. No
fetch,async,WebWorker, external APIs, or CDNs after page load. - Zero PII. No storage, logging, or transmission of personal/identifiable data.
- Storage: All client storage forbidden —
sessionStorage,localStorage,cookies,IndexedDB. All state is in-memory (CONTRACT.md§1.1). - Routing: Tools in
tools/use../relative paths to reach root assets. Index usestools/andguides/prefixes. Absolute URLs only for the MCP registry surfaces (.well-known/mcp.json,mcp/catalog.json,mcp/server.json) and external MCP endpoints. - License: CC BY 4.0. Code readable, commented, attribution-ready.
- Reader-facing copy (CONTRACT §1.4): no em-dashes (en-dash ranges fine; §1.3 banner exempt) and no build codes (
Wave N,W-A…W-G,D0) in public HTML prose orchaingraph.jsondescriptions. Gate:node scripts/check-copy-hallmarks.mjs; counts in its baseline only go down. - Author every code/data file with Write/Edit — NEVER a bash heredoc,
echo, orprintf(quote/$mangling silently truncates files). execution_hash— callexecutionHash(policy_parameters, output_payload)fromchaingraph/kernels/_hash.mjs. NEVER hand-build the preimage orJSON.stringifyit. One canonicalization exists (RFC 8785 / JCScgCanon). Ad-hoc canon tripslint-forbidden-hash; fix withnode chaingraph/kernels/fix-hash-scheme.mjs. Copy the hash path from a proven kernel (e.g.art-213).- Derived artifacts: never edit in a PR.
sitemap.xml,mcp/catalog.json,mcp/server.json,.well-known/mcp.json,llms.txt,tools.html,index.htmlgenerated sections,chaingraph/chaingraph-hub.html, and count sentinels have a single writer (derived-artifacts-regen.yml, onmain). Freshness gates are advisory on PRs; details in skillwave-checklist.
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.
- 3d ago Changed · -62 lines · -2,285 tokens per session c98d729fa7bb
- 26d ago Changed · +6 lines · +121 tokens per session 46910e96bdc9
- 1mo ago Changed · +108 tokens per session 168c8a260ae5
- 1mo ago Changed · +56 tokens per session dbb62b6b0140
- 1mo ago First seen · 102 lines · 3,384 tokens per session scan A 2b696fb397af
ainumbers CLAUDE.md is an instructions file published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 1,384 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.