agent-os AGENTS.md

Repository instructions for the `kai-linux/agent-os` project, including guidance for agent instruction files, delivery, and Git practices. They say completed work should normally be committed and pushed.

In plain words
What is it for?
Keeping `AGENTS.md` and `CLAUDE.md` aligned, staging only relevant files, and following the project's delivery rule.
Why use it?
They set shared expectations for finishing work and help prevent unrelated changes or poor commit hygiene.

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/kai-linux/agent-os/agents-md
Clone the repo
git clone --depth 1 https://github.com/kai-linux/agent-os

Made for: Codex, OpenCode.

Per session 109 This file is loaded in full into every session.
When invoked 109 The same file — it is already loaded in full.
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 $0.00109 $0.00109
Opus 5 $0.00055 $0.00055
Sonnet 5 $0.00022 $0.00022
Haiku 4.5 $0.00011 $0.00011

Measured 2d ago against content hash de32254d9291, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-os 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.

AGENTS.md · 14 lines

What it actually says

AGENTS.md

Companion doc for Claude Code: CLAUDE.md. Both files describe this repo for different coding agents — keep them in sync.

Default Delivery Rule

  • When a task is complete, commit your changes and push to the remote unless the user explicitly says not to.

Git Hygiene

  • Do not commit unrelated user changes.
  • If the worktree is dirty, stage only the files touched for the current task.
  • Do not amend commits unless the user explicitly asks for it.
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 · 14 lines · 109 tokens per session scan A de32254d9291

Subscribe to this mod's changes

agent-os AGENTS.md is an instructions file published in the GitHub repository kai-linux/agent-os (5 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session, about $0.0005 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 2026-08-31.

Related

Other instructions, from other repositories