using-autopus

using-autopus is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 16 tokens per session (1,819 once invoked), scanned A, original, MIT.

An installation and usage guide for Autopus-ADK, a harness that adds coding methods, model routing, hooks, session continuity, and project quality rules to coding command-line tools.

In plain words
What is it for?
Use it to set up full or lightweight Autopus-ADK installations for tools such as Claude Code and Codex.
Why use it?
It explains how to install, configure, inspect, update, or remove the harness instead of relying on undocumented commands.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; mentions AGENTS.md; mentions Codex.

Good fit Use it to set up full or lightweight Autopus-ADK installations for tools such as Claude Code and Codex.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/using-autopus
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.

Any agent
npx skills add Insajin/autopus-adk --skill using-autopus
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

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 using-autopus

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/using-autopus/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/using-autopus)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/using-autopus"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/using-autopus/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for using-autopus

Your own site · 80×15
<a href="https://agentmods.dev/skills/insajin/autopus-adk/using-autopus"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/using-autopus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,819 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00016 $0.01819
Opus 5 $0.00008 $0.00910
Sonnet 5 $0.00003 $0.00364
Haiku 4.5 $0.00002 $0.00182

Measured 8d ago against content hash 112fe769b2d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

using-autopus 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 8d 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.

.omp/skills/using-autopus/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Autopus-ADK Skill

Autopus-ADK를 사용하여 코딩 CLI에 하네스를 설치하는 방법입니다.

설치 모드

Full Mode

모든 기능을 포함하는 완전한 하네스:

  • 방법론 (TDD/DDD/Double Diamond)
  • 모델 라우터
  • 인텐트 게이트
  • 세션 연속성
  • 훅 시스템

Lite Mode

핵심 기능만 포함하는 경량 하네스:

  • 아키텍처 문서
  • Lore 커밋 시스템
  • SPEC 엔진
  • 기본 훅

CLI 명령어

# 하네스 설치 (인터랙티브)
auto init

# 특정 모드로 설치
auto init --mode full
auto init --mode lite

# 특정 플랫폼에 설치
auto init --platforms claude-code
auto init --platforms codex,antigravity-cli

# 설치 상태 확인
auto doctor

# 하네스 업데이트
auto update

# 설치 제거
auto clean

설정 파일 (autopus.yaml)

mode: full
project_name: my-project
platforms:
  - claude-code
  - codex

methodology:
  mode: tdd
  enforce: true
  review_gate: true

hooks:
  pre_commit_arch: true
  pre_commit_lore: true
  react_ci_failure: false
  react_review: false

quality:
  default: balanced
  providers:
    claude: ultra
    codex: balanced

OMP와 OMP 품질 모드 분리

quality.default는 기존 전역 fallback입니다. OMP와 OMP를 함께 쓰면 quality.providers.claudequality.providers.codex를 선택적으로 추가해 서로 다른 Ultra/Balanced 모드를 사용할 수 있습니다.

auto quality provider claude ultra --apply
auto quality provider codex balanced --apply
auto quality provider claude inherit --apply
auto quality show

CLI에서는 claude-codeclaude의 alias로 허용하지만 YAML에는 canonical key claude를 저장합니다. Provider별 --apply는 해당 provider가 platforms에 구성된 경우에만 그 플랫폼을 갱신합니다. 기존 auto quality ultra|balanced --applyquality.default를 바꾸고 구성된 모든 플랫폼을 갱신합니다. 한 번의 실행에 지정한 --quality는 두 persisted provider override보다 우선하며 YAML은 수정하지 않습니다.

OMP Opus 5 기본 경로

OMP Ultra, Balanced 전략 역할, high-complexity 라우팅은 고정 모델 ID claude-opus-5를 사용합니다. OMP의 opus alias가 Opus 5를 선택하려면 2.1.219 이상이 필요합니다. Opus 5를 고정한 route_team workflow는 auto workflow doctor --route route_team에서 2.1.219 미만을 fail-closed합니다. 모델을 고정하지 않는 route_a는 기존 최소 버전 2.1.154를 유지합니다.

OMP provider opus on v2.1.219+ Before v2.1.219
Anthropic API Opus 5 Opus 4.8 on v2.1.154–v2.1.218
OMP Platform on AWS Opus 5 Opus 4.8 on v2.1.207–v2.1.218; Opus 4.7 before v2.1.207
Amazon Bedrock Opus 5 Opus 4.8 on v2.1.207–v2.1.218; Opus 4.6 before v2.1.207
Google Cloud Agent Platform Opus 5 Opus 4.8 on v2.1.207–v2.1.218; Opus 4.6 before v2.1.207
Microsoft Foundry Opus 4.6 Opus 4.6

Read the full file on GitHub · 191 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. 8d ago First seen · 191 lines · 16 tokens per session scan A 112fe769b2d4

Subscribe to this mod's changes

using-autopus is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 1,819 once invoked, about $0.0001 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 2026-09-03.