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.
npx agentmods add instructions/insajin/autopus-adk/agents-mdgit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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.
[](https://agentmods.dev/instructions/insajin/autopus-adk/agents-md)<a href="https://agentmods.dev/instructions/insajin/autopus-adk/agents-md"><img src="https://agentmods.dev/badge/instructions/insajin/autopus-adk/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02446 | $0.02446 |
| Opus 5 | $0.01223 | $0.01223 |
| Sonnet 5 | $0.00489 | $0.00489 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
autopus-adk AGENTS.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autopus-ADK Harness
이 섹션은 Autopus-ADK에 의해 자동 생성됩니다. 수동으로 편집하지 마세요.
- 프로젝트: autopus-adk
- 모드: full
- 플랫폼: claude-code, codex, antigravity-cli, opencode, omp
Installed Components
- Claude Skills: .claude/skills//SKILL.md
- Claude Agents: .claude/agents/autopus/
- Claude Rules: .claude/rules/autopus/
- Claude Hooks: .claude/hooks/autopus/
- Claude Settings: .claude/settings.json
- Claude Statusline: .claude/statusline.sh
- Claude Root Doc: CLAUDE.md
- Codex Native Skills: .codex/skills/codex-/SKILL.md
- Codex Agents: .codex/agents/
- Codex Hook Scripts: .codex/hooks/
- Codex Hook Registry: .codex/hooks.json
- Codex Config: .codex/config.toml
- Codex Plugin Router: @auto ... / $codex-auto-
- Gemini Skills: .gemini/skills/autopus//SKILL.md
- Gemini Agents: .gemini/agents/autopus/
- Gemini Rules: .gemini/rules/autopus/
- Gemini Commands: .gemini/commands/
- Gemini Hooks: .gemini/hooks/
- Gemini Settings: .gemini/settings.json
- Gemini Statusline: .gemini/statusline.sh
- Gemini Hook Registry: .agents/hooks.json
- Gemini Root Doc: GEMINI.md
- Gemini Plugin Bundle: .agents/plugins/autopus/
- Shared Commands: .agents/commands/
- OpenCode Rules: .opencode/rules/autopus/
- OpenCode Commands: .opencode/commands/
- OpenCode Agents: .opencode/agents/
- OpenCode Plugins: .opencode/plugins/
- OpenCode-owned Shared Skills: .agents/skills/
- OMP Skills: .omp/skills/
- OMP Agents: .omp/agents/
- OMP Rules: .omp/rules/
- OMP Commands: .omp/commands/
- Plugin Marketplace: .agents/plugins/marketplace.json
Language Policy
These settings are prompt instructions for every agent in this project. They are not mechanically enforced: no hook, linter, or CI gate inspects the language of comments, commit messages, or responses. The pre-commit Lore check validates the commit type prefix and sign-off trailers only, never the language. Treat a violation as a review finding, not as something a gate will catch.
- Code comments: en
- Commit messages: ko
- AI responses: ko
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.
- 2d ago First seen · 236 lines · 2,446 tokens per session scan A 215c6d5f4fd8
autopus-adk AGENTS.md is an instructions file published in the GitHub repository Insajin/autopus-adk (109 stars, last pushed yesterday), licensed MIT. It adds 2,446 tokens to every session, about $0.0122 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.
Other instructions, from other repositories
eigent AGENTS.md
AGENTS.md instructions for eigent-ai/eigent, covering eigent agent instructions, ui work, product terminology and validation.
Agentlas-OS GEMINI.md
Gemini CLI instructions for agentlas-ai/Agentlas-OS, covering gemini cli adapter, public release boundary, startup, default behavior and global command.
HARTOS CLAUDE.md
Claude Code instructions for hertz-ai/HARTOS, covering claude.md, project overview, master key - ai exclusion zone, branch discipline — main branch only (mandatory) and sibling repos — canonical filesystem paths.
orloj AGENTS.md
AGENTS.md instructions for OrlojHQ/orloj, covering orloj agent instructions, must-follow sync rules and working style.
autobot CLAUDE.md
Claude Code instructions for crystal-autobot/autobot, covering autobot, rules, code quality standards, ameba rules and verification checks.
mecha AGENTS.md
AGENTS.md instructions for ljchang/mecha, covering agents.md, orientation, before you start, before you finish and the traps.