aios AGENTS.md

Repository instructions for the rexleimo/aios project, including path conventions, workflow selection, project structure, and build and test commands. A repository is the project’s files and history managed by a version-control system such as Git.

In plain words
What is it for?
Use them when changing the AIOS project to resolve paths, choose the required workflow, organize modules, and run the specified build or test commands.
Why use it?
They tell the coding agent which project paths and workflow rules to follow, reducing mistakes caused by working from the wrong directory or skipping required checks.

Instructions file for CodexOpenCode

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/rexleimo/aios/agents-md
Clone the repo
git clone --depth 1 https://github.com/rexleimo/aios

Made for: Codex, OpenCode.

Per session 3,876 This file is loaded in full into every session.
When invoked 3,876 The same file — it is already loaded in full.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5 $0.03876 $0.03876
Opus 5 $0.01938 $0.01938
Sonnet 5 $0.00775 $0.00775
Haiku 4.5 $0.00388 $0.00388

Measured 2d ago against content hash 72ec386de133, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

aios AGENTS.md scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- RTK: `brew install rtk` or `curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh` (see https://github.com/rtk-ai/rtk#installation)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- RTK: `brew install rtk` or `curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh` (see https://github.com/rtk-ai/rtk#installation)
AGENTS.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Path Conventions (路径约定)

IMPORTANT: All relative paths in this document are relative to the PROJECT ROOT (current working directory), NOT AIOS_ROOT.

  • AIOS_ROOT - AIOS framework installation location (contains scripts/, package.json)
  • Project Root - Current working directory (contains .aios/, .codex/skills/, project state)
  • Paths like .aios/, .codex/skills/, docs/plans/ are relative to Project Root
  • Run pwd to see Project Root; echo $AIOS_ROOT to see framework location
  • See docs/architecture/path-resolution.md for detailed path resolution rules

Evaluate the AIOS workflow policy before creating a plan, selecting a skill, or dispatching work.

  1. direct and noop turns do not create a persistent plan or invoke a skill chain.
  2. guarded turns use only the required edit and verification gates.
  3. planned turns create or reuse one work-item plan, then execute only the Provider selected by the current rex Command.
  4. Do not insert a global bootstrap or compatibility skill chain. aios-workflow-router helps classify work but does not replace the Provider selected by the current Rex Capability Command.
  5. Invoke the selected Provider rather than paraphrasing it; use verification-before-completion before claiming a changed behavior is complete.

Project Structure & Module Organization

This repository is a local-first AI agent workspace centered on browser automation via MCP.

  • mcp-server/: TypeScript Playwright MCP server and local browser runtime.
  • scripts/run-local-browser-mcp.mjs: default MCP launcher for the repository-local Node/Playwright server.
  • mcp-server/src/index.ts: MCP server entry point and tool routing.
  • mcp-server/src/browser/: browser launcher, profile manager, auth checks, and tool actions.
  • config/: runtime configuration such as browser-profiles.json and safety-related settings.
  • .aios/memo/: Git-friendly project memo records generated by aios memo; runtime specs live in scripts/lib/specs/.
  • .aios/: gitignored project-local runtime state such as ContextDB sessions/exports, workspace metadata, active skill indexes, and bootstrap task queues.
  • docs/plans/: implementation and design plans.
  • .aios/tasks/: generated task queues and repo-managed task metrics/templates live here.

Read the full file on GitHub · 279 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. 2d ago First seen · 279 lines · 3,876 tokens per session scan C 72ec386de133

Subscribe to this mod's changes

aios AGENTS.md is an instructions file published in the GitHub repository rexleimo/aios (52 stars, last pushed 3d ago), licensed MIT. It adds 3,876 tokens to every session, about $0.0194 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.