aios-interception-runtime

A setup guide for RTK and Caveman, local tools that shorten command and agent output before it reaches the conversation.

In plain words
What is it for?
Use it to detect, install, configure, and verify these output-compression tools for supported coding-agent clients.
Why use it?
It reduces the amount of repeated terminal text the agent must process while keeping the underlying work local.

Skill for Claude CodeCodex

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-interception-runtime
Any agent
npx skills add rexleimo/aios --skill aios-interception-runtime
Clone the repo
git clone --depth 1 https://github.com/rexleimo/aios

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,877 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00080 $0.01877
Opus 5 $0.00040 $0.00938
Sonnet 5 $0.00016 $0.00375
Haiku 4.5 $0.00008 $0.00188

Measured 3d ago against content hash 4b1bdbd13e65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

aios-interception-runtime 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 3d 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.

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh

Makes network callslowCapability

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

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh
skill-sources/aios-interception-runtime/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RTK + Caveman 社区工具安装配置指南

AIOS 原生拦截运行时已废弃。Token 压缩改由社区维护的 RTKCaveman 处理。

  • RTK (https://github.com/rtk-ai/rtk) — Rust CLI 代理,过滤和压缩命令输出 60-90%。单二进制,<10ms 开销,100+ 支持命令。本地运行,无外部服务。
  • Caveman (https://github.com/JuliusBrussee/caveman) — Claude Code skill/插件,压缩 agent 输出 token ~75%。保持技术准确性,仅压缩表述风格。本地 prompt skill。

一、自动安装

aios init 会自动检测并安装 RTK + Caveman(带有安装确认提示):

# 交互式安装(会提示确认)
node scripts/aios.mjs init --agent <claude|codex|gemini|opencode>

# 跳过确认提示(用于 CI/无人值守场景)
node scripts/aios.mjs init --yes-compression-tools

# 仅检测不安装
node scripts/aios.mjs init --dry-run

安装后 aios init 会自动运行 rtk init -g 为检测到的客户端注册 hook/plugin。

二、手动安装

RTK

# macOS (推荐)
brew install rtk

# Linux / macOS / WSL
curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh

# Windows (下载预编译二进制)
# 从 https://github.com/rtk-ai/rtk/releases 下载 rtk-x86_64-pc-windows-msvc.zip
# 解压到 PATH 中的目录(如 C:\Users\<you>\.local\bin)

# Cargo
cargo install --git https://github.com/rtk-ai/rtk

# 验证
rtk --version   # 应显示 rtk 0.28.2+
rtk gain        # 查看 token 节省统计
RTK 初始化
rtk init -g                     # Claude Code / Copilot (默认)
rtk init -g --gemini            # Gemini CLI
rtk init -g --codex             # Codex (OpenAI)
rtk init --agent cursor         # Cursor
rtk init --agent windsurf        # Windsurf
rtk init --agent cline          # Cline / Roo Code
rtk init --agent hermes         # Hermes

Caveman

# macOS / Linux / WSL / Git Bash
curl -fsSL https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.sh | bash

# Windows (PowerShell 5.1+)
$installer = Join-Path $env:TEMP 'caveman-install.ps1'
irm https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.ps1 -OutFile $installer
powershell -NoProfile -ExecutionPolicy Bypass -File $installer
Remove-Item $installer -Force

安装后约 30 秒。需要 Node >= 18。会自动检测已安装的客户端并跳过没有的。 安全重复运行。

Read the full file on GitHub · 185 lines

Files

What ships with it

1 file 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. 3d ago First seen · 185 lines · 80 tokens per session scan C 4b1bdbd13e65

Subscribe to this mod's changes

aios-interception-runtime is a skill published in the GitHub repository rexleimo/aios (52 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 1,877 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

obsidian-cli

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…

breferrari/obsidian-mind · 102 tokens

gog-workspace

Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.

AtomicBot-ai/atomic-agent · 68 tokens

apple-calendar

Read macOS Calendar events via the icalBuddy CLI and create events via AppleScript (osascript). Use to check the user's calendar, agenda, upcoming events, or add an event on macOS.

AtomicBot-ai/atomic-agent · 45 tokens

apple-reminders

Manage Apple Reminders via the remindctl CLI on macOS — list, add, complete, delete, manage lists.

AtomicBot-ai/atomic-agent · 31 tokens

apple-notes

Manage Apple Notes via the memo CLI on macOS — create, view, search, edit, export.

AtomicBot-ai/atomic-agent · 27 tokens

handover

Use when wrapping up or capturing the current state of a coding session — writes a short, dated entry to the repo's RepoHandover.md so a future agent or you can resume without grepping archived sessions. Triggers on "handover", "hand off", "write handover", "capture state", "checkpoint this session".

jazzyalex/agent-sessions · 71 tokens