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/elizaos/eliza/claude-mdgit clone --depth 1 https://github.com/elizaOS/elizaWhat 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 | $0.05897 | $0.05897 |
| Opus 5 | $0.02949 | $0.02949 |
| Sonnet 5 | $0.01179 | $0.01179 |
| Haiku 4.5 | $0.00590 | $0.00590 |
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.
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.
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.mdand itsREADME.md. A local guide adds package-specific architecture, commands, and validation requirements; repository-wide rules in this guide remain binding. CLAUDE.mdandAGENTS.mdin the same directory must be byte-for-byte identical. AuthorCLAUDE.md, copy the finished content toAGENTS.md, and runbun run check:agents-claude.- The
AGENTS.mdfiles underpackages/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
- 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. - Identify the owning workspace and read its local guide, README, manifest, exports, and relevant tests.
- Search for callers and contract tests before changing a public type, route, event, environment variable, script, or package export.
- Use the narrowest relevant command while iterating, then run the required package and repository gates before declaring the work complete.
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.
- yesterday First seen · 486 lines · 5,897 tokens per session scan A 8c3886754efd
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.
Other instructions, from other repositories
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
AgentEval copilot-instructions.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
AgentEval tracing.instructions.md
Guidelines for implementing trace recording and replay.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
skill-based-architecture AGENTS.md
Instructions for WoJiSama/skill-based-architecture, covering agents.md, quick routing (survives context truncation), auto-triggers and red flags — stop.