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.
npx agentmods add instructions/cbirkbeck/aintlib/claude-mdgit clone --depth 1 https://github.com/CBirkbeck/AINTLIBWhat 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 | $0.02269 | $0.02269 |
| Opus 5 | $0.01135 | $0.01135 |
| Sonnet 5 | $0.00454 | $0.00454 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
AINTLIB 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 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.
This is a copy
97% identical to AINTLIB AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AINTLIB — rules for AI sessions
AINTLIB is an AI-reviewed number-theory library — built like mathlib, but maintained by AI
agents and tolerant of work-in-progress. It is one Lake workspace with every NT project side
by side under projects/<P>/, all on a single mathlib that is bumped to latest daily. Because
it is one build unit, any result can import any other — that is the entire point.
Work happens across machines, through GitHub (CBirkbeck/AINTLIB). Identify your role below and
follow that section.
Structure
main— the integrated library. Always builds. Bumped to latest mathlib daily and centrally.sorryis allowed here as an explicit work-in-progress marker.dev/<project>branches — each project's frontier, where new theorems are proved. Each carries its own dev ticket system.- Two ticket systems. Dev tickets (per project, on its
dev/<project>branch) track new math. Cleanup tickets (onmain) are GitHub issues labelled by lane (see Worker system below) and track dedup / golf / style / cross-linking / generalisation / proof-decomposition. The handoff between them is merging a dev branch intomain.
Your working copy — all workers share ONE clone on this machine
Do not clone AINTLIB per worker. Use a git worktree per dev branch, so every worker runs in
parallel off the same .git:
# once, from the main AINTLIB checkout (which stays on `main`):
git worktree add ../aintlib-adic dev/adic-spaces
git worktree add ../aintlib-padic dev/padic
git worktree add ../aintlib-hasse dev/hasse-weil
Each worker then lives in its own directory (../aintlib-<proj>) on its own branch — separate files
and a separate .lake build, fully isolated, no clobbering. In your worktree: lake exe cache get,
then build. Commit on your dev branch; PR to main when a ticket is done; git rebase main after
the daily bump (your worktree shares all of main's refs locally — no fetch needed). Until AINTLIB
publishes its own olean cache, the first build in each worktree compiles the project tree from
source once (mathlib still comes from cache); after that it is incremental.
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 · 128 lines · 2,269 tokens per session scan A a1edfdecae15
AINTLIB CLAUDE.md is an instructions file published in the GitHub repository CBirkbeck/AINTLIB (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,269 tokens to every session, about $0.0113 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to AINTLIB AGENTS.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.