agentmods.dev

aios-project-system

aios-project-system is a skill for Claude Code, Codex from rexleimo/aios. It costs 34 tokens per session (800 once invoked), scanned A, original, MIT.

A map of the AIOS repository's architecture, stored state, browser tools, skill sources, and execution rules. AIOS is a project system for coordinating coding-agent workflows.

In plain words
What is it for?
Use it before changing AIOS workflows, tasks, browser operations, skill synchronization, or other project-level automation.
Why use it?
It helps changes follow the repository's authoritative structure instead of editing generated files or bypassing required checks.

Skill for Claude CodeCodex

not rated 52 yesterday A scan 34 tokens original MIT
View the source file rexleimo/aios
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 skills/rexleimo/aios/aios-project-system
Any agent
npx skills add rexleimo/aios --skill aios-project-system
Clone the repo
git clone --depth 1 https://github.com/rexleimo/aios

Made for: Claude Code, Codex.

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 aios-project-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/rexleimo/aios/aios-project-system.svg)](https://agentmods.dev/skills/rexleimo/aios/aios-project-system)
Your own site
<a href="https://agentmods.dev/skills/rexleimo/aios/aios-project-system"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/aios-project-system.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 800 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00800
Opus 5 $0.00017 $0.00400
Sonnet 5 $0.00007 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 5d ago against content hash 6b8eb532664c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aios-project-system 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 5d 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.

skill-sources/aios-project-system/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIOS Project System

Overview

Use this skill as the repository map for aios. It explains where state lives, how automation actually runs, and which files are authoritative before you edit tasks, workflows, or browser operations.

This skill is a map, not a router. For task routing, use aios-workflow-router; execute only the Provider selected by the current Rex Capability Command.

Core Topology

  • CLAUDE.md / AGENTS.md / GEMINI.md: per-client project-level behavior contract and architecture overview (each client loads its own instruction file).
  • skill-sources/*/SKILL.md: canonical skill sources (edit here, never edit generated copies).
  • Generated repo-local skills per client: .codex/skills, .claude/skills, .gemini/skills, .opencode/skills, .agents/skills — emitted from skill-sources/ via config/skills-sync-manifest.json.
  • Agent promotion and workflow enablement are evidence-gated: use agents smoke for core-risk rollout evidence, then skill verify-training to block changed skills until SkillOpt training is accepted.
  • scripts/lib/specs/*.json: runtime specifications and limits.
  • tasks/{pending,done,failed}: task queue and outcomes.
  • scripts/run-browser-use-mcp.sh: default browser MCP launcher (bridges to ai-browser-book/mcp-browser-use).
  • mcp-server/: legacy Playwright MCP implementation retained for compatibility workflows.
  • docs/plans/: design, implementation, and postmortem documents.

Runtime Truths (Do Not Skip)

  • The primary browser MCP server label is mcp-browser-use; do not add compatibility aliases for old browser MCP names.
  • mcp-server/src/index.ts still exposes Playwright browser_* tools, but treat that path as legacy/compatibility.
  • If both mcp-browser-use and chrome-devtools are available, use mcp-browser-use for normal browser automation and reserve chrome-devtools for debugging only.
  • For interactive runs, explicitly prefer chrome.launch_cdp { port: 9222, user_data_dir: '~/.chrome-cdp-profile' }, then browser.connect_cdp.
  • Repo-local skill SKILL.md files can drift from site UI; treat them as runbooks that require live verification.
  • Prefer page.extract_text / page.get_html evidence before using page.screenshot.
  • Repo-local discoverable skills are generated under each client's skill root (.codex/skills, .claude/skills, .gemini/skills, .opencode/skills, .agents/skills) from skill-sources/ — do not create ad-hoc skill roots such as .baoyu-skills/*/SKILL.md. .baoyu-skills/ is extension-config territory, not a skill root. Edit canonical sources under skill-sources/, then run skill sync.
  • Keep safety constraints aligned with scripts/lib/specs and the skill-constraints skill.

Read the full file on GitHub · 46 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 46 lines · 34 tokens per session scan A 6b8eb532664c

Subscribe to this mod's changes

aios-project-system is a skill published in the GitHub repository rexleimo/aios (52 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 800 once invoked, about $0.0002 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.

Building agentsai-agentaiosautomationbrowser-automationclaude-codeclicodex-clirepo
Related

Other skills, from other repositories

linkedin

Use when handling MediaUse LinkedIn automation tasks, including jobs and people search, timeline and inbox retrieval, profile reads, safe connect/message flows, and Sales Navigator workflows, with Windows install, key onboarding, strict context/auth flow, full dynamic command map, and safety/rate controls.

mediause/agent-skills · 59 tokens

xiaohongshu

Standardized Xiaohongshu skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full Xiaohongshu dynamic command map, and safety/rate controls.

mediause/agent-skills · 43 tokens

arxiv

Standardized arXiv skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full arXiv dynamic command map, and safety/rate controls.

mediause/agent-skills · 39 tokens

chatgpt

Standardized ChatGPT skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full ChatGPT dynamic command map, and safety/rate controls.

mediause/agent-skills · 38 tokens

douyinv2

Standardized douyinv2 skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full douyinv2 dynamic command map, and safety/rate controls.

mediause/agent-skills · 43 tokens

fifa2026

Standardized fifa2026 skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full fifa2026 dynamic command map, and safe read-oriented execution controls.

mediause/agent-skills · 42 tokens