agentmods.dev

CarpeOS AGENTS.md

CarpeOS AGENTS.md is an instructions file for Codex, OpenCode from innocarpe/CarpeOS. It costs 1,988 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for CarpeOS, including its architecture boundaries, documentation practices, installation guidance, and rules for what agents may add.

In plain words
What is it for?
Use them when changing CarpeOS code or documentation, installing the agent guide, deciding where information belongs, or checking repository boundaries.
Why use it?
They keep contributors and coding agents consistent and prevent private data, credentials, or unsupported product claims from entering the project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

not rated 0 21d ago A scan 1,988 tokens original Apache-2.0
View the source file innocarpe/CarpeOS innocarpe.github.io
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/innocarpe/carpeos/agents-md
Clone the repo
git clone --depth 1 https://github.com/innocarpe/CarpeOS

Made for: Codex, OpenCode.

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 CarpeOS AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/innocarpe/carpeos/agents-md.svg)](https://agentmods.dev/instructions/innocarpe/carpeos/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/innocarpe/carpeos/agents-md"><img src="https://agentmods.dev/badge/instructions/innocarpe/carpeos/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,988 This file is loaded in full into every session.
When invoked 1,988 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 5.1 $0.01988 $0.01988
Opus 5 $0.00994 $0.00994
Sonnet 5 $0.00398 $0.00398
Haiku 4.5 $0.00199 $0.00199

Measured 5d ago against content hash 76c1ba3e3c2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

CarpeOS 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 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.

AGENTS.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CarpeOS Agent Guide

This file defines repository-local guidance for AI agents working on CarpeOS.

Primary Boundary

CarpeOS is a public implementation for private knowledge systems.

Do not add:

  • real user project names;
  • real session transcripts;
  • real private repository URLs;
  • local user paths;
  • production logs;
  • credentials, tokens, cookies, or private keys;
  • runtime database exports;
  • private Obsidian vault exports.

Use fictional, generic, synthetic examples only.

Documentation Rules

  • README.md is the canonical English README: agents and humans should learn what the product is, how it works, how to install, and what is shipped. Keep the hero clean (no contradictory status lines or DoD link farms). Keep substantive sections (why, who, capabilities, install paths, status, repo boundary). Do not gut those for line-count vanity.
  • Full product-line archaeology (every historical major row) and long agent install essays belong in docs/PRD.md / docs/maintainers/ / this file — not as a second changelog under the hero.
  • README.ko.md should track the same substance in Korean.
  • Planned features must be described as planned.
  • Do not document commands as working unless they have been verified.
  • Do not claim adapters, MCP tools, sync, projections, or hosted deployment are complete until implementation and tests exist.
  • After every MAJOR package cut, complete docs/maintainers/major-release-surface.md and run node scripts/check-major-release-surface.mjs (README needs the current @innocarpe/[email protected] / vX.Y.Z pin, cleanly).

Agent install (idempotent)

Keep private data out of the git tree.

  1. Prefer npm i -g @innocarpe/carpeos then carpeos setup plan / carpeos setup run --apply (or scripts/install.sh).
  2. Capture hooks: carpeos setup hooks install --apply.
  3. From a checkout: node scripts/install-local.mjs run --apply.
  4. Never commit ~/.carpeos, credentials, or real session data.
  5. Do not invent alternate install paths; setup registers MCP and optional hooks.
  6. Releases: SemVer + vX.Y.Z only — skills/carpeos-release/SKILL.md and ./scripts/install-release-skill.sh.

Read the full file on GitHub · 193 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. 5d ago First seen · 193 lines · 1,988 tokens per session scan A 76c1ba3e3c2a

Subscribe to this mod's changes

CarpeOS AGENTS.md is an instructions file published in the GitHub repository innocarpe/CarpeOS (0 stars, last pushed 21d ago), licensed Apache-2.0. It adds 1,988 tokens to every session, about $0.0099 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.

ai-agentscloudflareknowledge-managementlocal-firstmcpobsidian
Related

Other instructions, from other repositories

chamber CLAUDE.md

Instructions for abm9111/chamber, covering working on chamber, the gates that matter are the probes, not the tests, verification rules that have each been paid for, traps in this codebase and law worth not breaking.

abm9111/chamber · 1,351 tokens

Molio CLAUDE.md

Claude Code instructions for zhuzhaoyun/Molio, covering molio — 让你的积累，在 ai 时代持续产生价值, project structure (pnpm monorepo), build & dev commands, desktop 构建与运行 and docker / nas 一键部署.

zhuzhaoyun/Molio · 4,452 tokens

obsidian-mind CLAUDE.md

Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.

breferrari/obsidian-mind · 9,405 tokens

obsidian-mind AGENTS.md

AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.

breferrari/obsidian-mind · 1,145 tokens

obsidian-llm-wiki AGENTS.md

AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.

green-dalii/obsidian-llm-wiki · 7,700 tokens

Khaos-Brain AGENTS.md

Instructions for liuyingxuvka/Khaos-Brain, covering repository expectations, bootstrap, start here, purpose and github publish default.

liuyingxuvka/Khaos-Brain · 4,956 tokens