What is ainumbers CLAUDE.md?

Build instructions for the deployable ainumbers fintech website, including its HTML pages, standalone tools, integration guides, and MCP manifests. It identifies CONTRACT.md as the main specification and lists important implementation constraints.

Use it when building or modifying ainumbers pages, tools, guides, manifests, or the site's MCP and export behavior.

It tells coding agents which files define the product contract and which restrictions apply before they edit the site. This helps avoid breaking the self-contained pages, tool manifests, or privacy requirements.

ainumbers CLAUDE.md — Instructions file for coding agents by PostOakLabs: Build instructions for the deployable ainumbers fintech website, i

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/claude-md

Clone the repo

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

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/postoaklabs/ainumbers/claude-md.svg)](https://agentmods.dev/instructions/postoaklabs/ainumbers/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/postoaklabs/ainumbers/claude-md"><img src="https://agentmods.dev/badge/instructions/postoaklabs/ainumbers/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,384 This file is loaded in full into every session.

When invoked 3,384 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	$0.03384	$0.03384
Opus 5	$0.01692	$0.01692
Sonnet 5	$0.00677	$0.00677
Haiku 4.5	$0.00338	$0.00338

Measured 3d ago against content hash 2b696fb397af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 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.md first.

Role: Deterministic, privacy-first fintech web engineer.

SSOT: CONTRACT.md — read in full before generating, modifying, or validating any file.

🗂️ Repository Structure

ainumbers/
├── CONTRACT.md        ← SSOT — read before any build
├── index.html         ← Main dashboard (tool grid, category filters, search)
├── sitemap.html / contact.html / about.html
├── tools/             ← standalone tool HTML files (numbered, pf-, rbe-, named)
├── guides/            ← integration hub HTML files (*-hub.html)
├── manifests/         ← MCP tool manifests (one per tool)
├── sitemap.xml / robots.txt / llms.txt

Canonical tool template: tools/152-baas-provider-comparator.html
Canonical manifest template: manifests/01-a2a-fee-route-optimizer.manifest.json

🔒 Non-Negotiable Constraints

Single self-contained .html per 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. (ain_lang sessionStorage exemption removed — lang toggle deferred; see CONTRACT.md §1.1.)
Routing: Tools in tools/ must use ../ relative paths to reach root assets. Index uses tools/ and guides/ prefixes for all internal links. Absolute URLs reserved strictly for suite-registry.json & external MCP endpoints.
License: CC BY 4.0. Code must be readable, commented, and attribution-ready.
Reader-facing copy (CONTRACT §1.4): Public HTML prose and chaingraph.json descriptions must pass the copy-hallmarks gate — no em-dashes (en-dash ranges fine; §1.3 banner exempt) and no build codes (Wave N, W-A…W-G, D0) in visible text. Gate: node scripts/check-copy-hallmarks.mjs (in preflight + CI); scripts/copy-hallmarks-baseline.json shields unswept legacy debt, counts only go down.
Author every code/data file with the Write/Edit tools — NEVER a bash heredoc, echo, or printf. Kernel/HTML/JSON content is full of ', backticks, and $; piping it through a shell produces unterminated-quote / unexpected EOF errors and silently-truncated files. The JS-syntax gate is the backstop, but write files directly and the failure never happens.
execution_hash — call executionHash(policy_parameters, output_payload) from chaingraph/kernels/_hash.mjs. NEVER hand-build the {policy_parameters, output_payload} preimage or JSON.stringify it yourself. There is exactly one correct canonicalization (RFC 8785 / JCS cgCanon) and it lives in _hash.mjs. Ad-hoc canonicalization trips lint-forbidden-hash ("Scheme E"); if it ever does, run node chaingraph/kernels/fix-hash-scheme.mjs. Copy the hash path from a proven kernel (e.g. art-213).

Read the full file on GitHub · 102 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.

3d ago First seen · 102 lines · 3,384 tokens per session scan A 2b696fb397af

Subscribe to this mod's changes

ainumbers CLAUDE.md is an instructions file published in the GitHub repository PostOakLabs/ainumbers (5 stars, last pushed 3d ago), licensed MIT. It adds 3,384 tokens to every session, about $0.0169 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 CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md — repo/ Build Directive

🗂️ Repository Structure

🔒 Non-Negotiable Constraints

What this file has done since we first saw it

Other instructions, from other repositories

ATF-AI copilot-instructions.md

Vibe-Research AGENTS.md

clawock AGENTS.md

kiasumiles AGENTS.md

waylMCP CLAUDE.md

agent-memory AGENTS.md