ait: Instructions file for Claude Code

CLAUDE.md

ait CLAUDE.md is an instructions file for Claude Code from m24927605/ait. It costs 1,441 tokens per session, scanned A, original, MIT.

A project instruction file for ait, an AI-agent-friendly version-control layer built on top of Git. It explains the repository, its technology, layout, and authoritative documents.

In plain words
What is it for?
Use it to guide work on ait, including locating the Python and SQLite code, following the repository structure, and running the commands defined by the project.
Why use it?
It gives coding agents consistent project context and tells them to follow the documented specification when code and documentation disagree.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is m24927605/ait's own configuration. It tells Claude Code how to work on ait itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ait configures →

Reuse

Borrowing it

Nothing to install: this file belongs to m24927605/ait. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/m24927605/ait/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/m24927605/ait

Made for: Claude Code.

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.

agentmods badge for ait CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m24927605/ait/claude-md.svg)](https://agentmods.dev/instructions/m24927605/ait/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/m24927605/ait/claude-md"><img src="https://agentmods.dev/badge/instructions/m24927605/ait/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,441 This file is loaded in full into every session.
When invoked 1,441 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01441 $0.01441
Opus 5 $0.00720 $0.00720
Sonnet 5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 6d ago against content hash 77aad528b4e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ait 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 6d 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 · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file gives Claude Code the project-specific context it needs to work on this repository safely and consistently. It mirrors the rules in AGENT.md but adds the technical details Claude Code needs (stack, commands, layout, entry points).

When AGENT.md and this file disagree, treat them as equally authoritative and ask before diverging.

Project Overview

ait is an AI-agent-native VCS layer that sits on top of Git. It adds structured intent tracking, isolated attempts, queryable execution history, and durable linkage between attempts and Git commits. It is not a replacement for Git.

Canonical specs live in docs/:

  • docs/ai-vcs-mvp-spec.md — v1 spec (frozen surface)
  • docs/implementation-notes.md — non-blocking clarifications and known limits
  • docs/protocol-appendix.md — daemon protocol details
  • docs/implementation-plan.md — milestones, acceptance criteria, breakdown
  • docs/parallel-development.md — parallel work coordination

Treat the spec as the source of truth. If implementation and spec disagree, that is a bug to be reviewed, not a silent divergence.

Tech Stack

  • Python >=3.14 (see pyproject.toml)
  • SQLite via stdlib sqlite3
  • stdlib unittest for tests
  • stdlib argparse, socket, subprocess — no runtime dependencies

The project must stay dependency-free unless a new dependency is explicitly approved and documented.

Repository Layout

src/ait/
  __init__.py
  cli.py                # argparse entry point (`ait ...`)
  app.py                # high-level operations (init/intent/attempt/show/...)
  config.py             # .ait dir bootstrap, install_nonce, local config
  repo.py               # git repo root resolution, repo_id derivation
  ids.py                # ULID generation
  hooks.py              # post-rewrite hook installer
  workspace.py          # worktree provisioning, commit helpers, ref updates
  daemon.py             # daemon process lifecycle (start/stop/serve)
  daemon_transport.py   # NDJSON unix socket transport
  protocol.py           # event envelope + payload schemas and validation
  events.py             # event handlers, dedupe, reaper, lifecycle updates
  verifier.py           # succeeded/promoted/failed determination
  query.py              # DSL parser, whitelisted fields, SQL lowering, blame
  reconcile.py          # post-rewrite reconciliation
  db/
    __init__.py         # re-exports
    core.py             # connect_db, run_migrations, meta table helpers
    schema.py           # migrations tuple, SCHEMA_VERSION
    repositories.py     # typed insert/get/list helpers per table
tests/
  test_*.py             # stdlib unittest
docs/                   # see above
AGENT.md                # base working rules
CLAUDE.md               # this file
pyproject.toml

Read the full file on GitHub · 172 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.

  1. 6d ago First seen · 172 lines · 1,441 tokens per session scan A 77aad528b4e3

Subscribe to this mod's changes

ait CLAUDE.md is an instructions file published in the GitHub repository m24927605/ait (6 stars, last pushed 3mo ago), licensed MIT. It adds 1,441 tokens to every session, about $0.0072 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens