Borrowing it
Nothing to install: this file belongs to innocarpe/CarpeOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/innocarpe/CarpeOS/main/AGENTS.mdgit clone --depth 1 https://github.com/innocarpe/CarpeOSWrote 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/innocarpe/carpeos/agents-md)<a href="https://agentmods.dev/instructions/innocarpe/carpeos/agents-md"><img src="https://agentmods.dev/badge/instructions/innocarpe/carpeos/agents-md/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.
<a href="https://agentmods.dev/instructions/innocarpe/carpeos/agents-md"><img src="https://agentmods.dev/badge/instructions/innocarpe/carpeos/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01988 | $0.01988 |
| Opus 5.5 | $0.00795 | $0.00795 |
| Sonnet 5.5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
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 1mo 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 — 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.mdis 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.mdshould 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.mdand runnode scripts/check-major-release-surface.mjs(README needs the current@innocarpe/[email protected]/vX.Y.Zpin, cleanly).
Agent install (idempotent)
Keep private data out of the git tree.
- Prefer
npm i -g @innocarpe/carpeosthencarpeos setup plan/carpeos setup run --apply(orscripts/install.sh). - Capture hooks:
carpeos setup hooks install --apply. - From a checkout:
node scripts/install-local.mjs run --apply. - Never commit
~/.carpeos, credentials, or real session data. - Do not invent alternate install paths; setup registers MCP and optional hooks.
- Releases: SemVer +
vX.Y.Zonly —skills/carpeos-release/SKILL.mdand./scripts/install-release-skill.sh.
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.
- 1mo ago First seen · 193 lines · 1,988 tokens per session scan A 76c1ba3e3c2a
CarpeOS AGENTS.md is an instructions file published in the GitHub repository innocarpe/CarpeOS (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,988 tokens to every session, about $0.0080 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.