AI-Inner-Os: Instructions file for Claude Code

CLAUDE.md

AI-Inner-Os CLAUDE.md is an instructions file for Claude Code from SummerSec/AI-Inner-Os. It costs 3,502 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for an AI coding assistant working on the AI-Inner-Os project. It explains the project structure, commands, data flow, and how to work across several coding tools.

In plain words
What is it for?
Use it when changing or checking AI-Inner-Os, switching personas, installing it for a platform, or tracing how its session hooks handle events.
Why use it?
It gives the assistant one agreed source of project rules, reducing guesswork about commands, architecture, and supported platforms.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_DATA} variable. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is SummerSec/AI-Inner-Os's own configuration. It tells Claude Code how to work on AI-Inner-Os 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 AI-Inner-Os configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to SummerSec/AI-Inner-Os. 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/SummerSec/AI-Inner-Os/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SummerSec/AI-Inner-Os

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 AI-Inner-Os CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/summersec/ai-inner-os/claude-md.svg)](https://agentmods.dev/instructions/summersec/ai-inner-os/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/summersec/ai-inner-os/claude-md"><img src="https://agentmods.dev/badge/instructions/summersec/ai-inner-os/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,502 This file is loaded in full into every session.
When invoked 3,502 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 $0.03502 $0.03502
Opus 5 $0.01751 $0.01751
Sonnet 5 $0.00700 $0.00700
Haiku 4.5 $0.00350 $0.00350

Measured 7d ago against content hash e87d32a00b5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

AI-Inner-Os 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 7d 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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 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.

Commands

npm run check            # syntax validation on all hook scripts
npm test                 # run tests (Node.js built-in test runner)
npm run lint             # alias for check
npm run switch-persona   # switch persona across all platform files
  # usage: npm run switch-persona -- <name|default|--list>
node scripts/install.js  # global install for all platforms
  # usage: node scripts/install.js --all
  # usage: node scripts/install.js --platform cursor
  # usage: node scripts/install.js --all --frequency high

No build step. Pure ESM, Node.js >= 18.

Architecture

AI Inner OS is a Claude Code plugin that injects a visible "inner monologue" layer into AI CLI sessions via lifecycle hooks. It also adapts to Codex CLI, Cursor, OpenCode CLI, Hermes Agent, and OpenClaw.

Data Flow (Claude Code)

SessionStart → reads protocol/SKILL.md → injects protocol as additionalContext
     ↓
PreToolUse → reads session state → injects "[即将执行] ToolName → target" context
     ↓
Tool executes
     ↓
PostToolUse (success) → normalizes event → appends to state → injects recent events
PostToolUseFailure    → normalizes failure → increments failureCount → injects error context
     ↓
PreCompact → saves compactedAt timestamp
PostCompact → injects compact-continuity context with recent events
SubagentStart/SubagentStop → records subagent lifecycle events
     ↓
Stop → deletes session state file

Single Source of Truth

protocol/SKILL.md is the canonical Inner OS protocol. hooks/lib/prompt.js reads it at runtime (strips YAML frontmatter). The static copies in codex/AGENTS.md, cursor/rules/inner-os-protocol.mdc, opencode/inner-os-rules.md, and hermes/hermes.md are manually synchronized — there is no automated derivation. hermes/skills/inner-os/SKILL.md is a Hermes-compatible skill variant with extended frontmatter. openclaw/skills/inner-os/SKILL.md is an OpenClaw-compatible skill variant with AgentSkills metadata. Optional skills live under skills/ and are copied to platform-specific skill directories when the platform has a native skill system.

Read the full file on GitHub · 196 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. 7d ago First seen · 196 lines · 3,502 tokens per session scan A e87d32a00b5c

Subscribe to this mod's changes

AI-Inner-Os CLAUDE.md is an instructions file published in the GitHub repository SummerSec/AI-Inner-Os (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3,502 tokens to every session, about $0.0175 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 2026-08-30.

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