eliza CLAUDE.md

Repository instructions for elizaOS, a monorepo containing the Eliza agent framework and its related applications, services, tools, tests, and plugins. A monorepo keeps many related projects in one code repository.

In plain words
What is it for?
Understanding the repository structure, following package-specific development rules, choosing validation commands, and keeping instruction files consistent.
Why use it?
It tells contributors which instructions and documentation to read before editing, and how paired CLAUDE.md and AGENTS.md files must be maintained and checked.

Instructions file

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/elizaos/eliza/claude-md
Clone the repo
git clone --depth 1 https://github.com/elizaOS/eliza
Per session 5,897 This file is loaded in full into every session.
When invoked 5,897 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.05897 $0.05897
Opus 5 $0.02949 $0.02949
Sonnet 5 $0.01179 $0.01179
Haiku 4.5 $0.00590 $0.00590

Measured yesterday against content hash 8c3886754efd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

eliza 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 yesterday.

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.

Origin

This is a copy

100% identical to eliza AGENTS.md — 0 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.

CLAUDE.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

elizaOS repository guide

This monorepo contains the elizaOS agent framework and the product stack built on it: the core runtime, standalone agent host, Eliza application, CLI, cloud services, native bridges, documentation, tests, and first-party plugins. Bootable Linux and AOSP distributions are maintained separately in elizaOS/os.

How repository instructions work

  • Read this guide before changing the repository.
  • Before working in a package or plugin, read the nearest CLAUDE.md and its README.md. A local guide adds package-specific architecture, commands, and validation requirements; repository-wide rules in this guide remain binding.
  • CLAUDE.md and AGENTS.md in the same directory must be byte-for-byte identical. Author CLAUDE.md, copy the finished content to AGENTS.md, and run bun run check:agents-claude.
  • The AGENTS.md files under packages/elizaos/src/migrate/__tests__/fixtures/ are migration inputs, not repository instructions. They are intentionally unpaired and must change only when the corresponding migration fixture changes.
  • Treat package manifests, exports, executable scripts, tests, and current source as the factual authority. Documentation is a map, not evidence that a feature still exists.

Naming

Write elizaOS, never ElizaOS. The npm scope is @elizaos/*. Use Eliza agents for agents built with the framework. The Eliza Classic plugin is the deliberate exception because it reimplements the 1966 chatbot.

Before editing

  1. Run git status --short --branch. This is a shared working tree and existing changes belong to their authors; do not discard, rewrite, or stage unrelated work.
  2. Identify the owning workspace and read its local guide, README, manifest, exports, and relevant tests.
  3. Search for callers and contract tests before changing a public type, route, event, environment variable, script, or package export.
  4. Use the narrowest relevant command while iterating, then run the required package and repository gates before declaring the work complete.

Read the full file on GitHub · 486 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. yesterday First seen · 486 lines · 5,897 tokens per session scan A 8c3886754efd

Subscribe to this mod's changes

eliza CLAUDE.md is an instructions file published in the GitHub repository elizaOS/eliza (19,210 stars, last pushed yesterday), licensed MIT. It adds 5,897 tokens to every session, about $0.0295 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to eliza AGENTS.md, differing in 0 lines, and is treated as a copy.