moat CLAUDE.md

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/majorcontext/moat/claude-md

Clone the repo

git clone --depth 1 https://github.com/majorcontext/moat

Per session 3,199 This file is loaded in full into every session.

When invoked 3,199 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	$0.03199	$0.03199
Opus 5	$0.01599	$0.01599
Sonnet 5	$0.00640	$0.00640
Haiku 4.5	$0.00320	$0.00320

Measured today against content hash aa1716770564, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

moat 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 today.

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 · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Moat runs AI agents in isolated containers with credential injection and full observability. Key features:

Isolated Execution - Each moat runs in its own container (Docker or Apple containers) with workspace mounting
Credential Injection - Transparent auth header injection via TLS-intercepting proxy (agent never sees raw tokens)
Smart Image Selection - Automatically selects container images based on moat.yaml runtime config
Full Observability - Captures logs, network requests, and traces for every run
Declarative Config - Configure agents via moat.yaml manifests
Multi-Runtime Support - Automatically uses Apple containers (macOS 26+) or Docker

Architecture

cmd/moat/           CLI entry point (Cobra commands)
internal/
  audit/             Tamper-proof audit logging with cryptographic verification
  claude/            Claude Code settings and Dockerfile generation
  cli/               Shared CLI helpers (environment parsing, mount helpers)
  codex/             Codex CLI settings and Dockerfile generation
  config/            moat.yaml parsing, mount string parsing
  container/         Container runtime abstraction (Docker and Apple containers)
  credential/        Secure credential storage (GitHub, Anthropic, AWS)
  daemon/            Proxy daemon lifecycle, Unix socket API, and run registration
  image/             Runtime-based image selection (node/python/go → base image)
  log/               Structured logging (slog wrapper)
  provider/          Provider registry and interfaces (CredentialProvider, AgentProvider)
  providers/         Provider implementations:
    aws/               AWS IAM role assumption and credential endpoint
    claude/            Claude Code CLI, grants, and config generation
    codex/             Codex CLI, grants, and config generation
    github/            GitHub token management and refresh
  run/               Run lifecycle management (create/start/stop/destroy)
  storage/           Per-run storage for logs, traces, network requests
  ui/                TTY-aware colored output and formatting helpers

Read the full file on GitHub · 216 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.

today First seen · 216 lines · 3,199 tokens per session scan A aa1716770564

Subscribe to this mod's changes

moat CLAUDE.md is an instructions file published in the GitHub repository majorcontext/moat (46 stars, last pushed 18d ago), licensed MIT. It adds 3,199 tokens to every session, about $0.0160 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 2026-09-01.

Planning

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

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