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/kingemma7/cursor-os/agents-mdgit clone --depth 1 https://github.com/KingEmma7/cursor-osWrote 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/kingemma7/cursor-os/agents-md)<a href="https://agentmods.dev/instructions/kingemma7/cursor-os/agents-md"><img src="https://agentmods.dev/badge/instructions/kingemma7/cursor-os/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 | $0.00418 | $0.00418 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
cursor-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 3d 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.
What it actually says
AGENTS.md — cursor-os
This repository ships Cursor OS — an installable operating layer that makes Cursor project-aware. It dogfoods its own contract: the rules below govern work in this repo.
What this project is
- An installable operating layer, not a framework. Keep the file set small and purposeful.
- The core promise: make Cursor project-aware by installing a contract, rules, memory docs, and prompts.
- The two highest-value assets are
template/AGENTS.md(the portable engineering contract) andtemplate/prompts/localize-cursor-os.md(the localization prompt). - Prefer practical, repo-specific guidance over generic process text.
Repository layout
template/— the kit that gets copied into other projects. Never assume a specific stack here.scripts/— the CLI and install/doctor APIs (init.mjs), read-only project detection (detect.mjs), and smoke test. Node built-ins only; no dependencies.examples/— concrete examples showing what localization looks like.docs/— this repo's own decision log (not installed into user projects).README.md,CHANGELOG.md,CONTRIBUTING.md— public-facing docs.
Working agreements
- Keep template files framework-neutral. Stack-specific guidance is generated during localization, not shipped as blanks.
- The installer must stay dependency-free and idempotent: never overwrite a user's existing files.
- Do not refer to prompts by number or sequence. Always use the full file path (e.g.,
prompts/plan-feature.md). - When you change the template's file set, update
README.md,CHANGELOG.md, and the installer's EXPECTED list inscripts/smoke-test.mjstogether. - Validate
package.jsonparses and runnpm test(the smoke test) before claiming the installer works.
Verification before done
Report what changed, why, how it was verified, and any remaining risks.
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.
- 3d ago First seen · 31 lines · 418 tokens per session scan A b43f82d0d0a6
cursor-os AGENTS.md is an instructions file published in the GitHub repository KingEmma7/cursor-os (2 stars, last pushed 22d ago), licensed MIT. It adds 418 tokens to every session, about $0.0021 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.
Other instructions, from other repositories
repository-harness AGENTS.md
Instructions for hoangnb24/repository-harness, covering agent instructions and harness.
repository-harness CLAUDE.md
Instructions for hoangnb24/repository-harness, covering project rules and harness.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.
trellis CLAUDE.md
Instructions for craigcossairt/trellis, a project described as: The structure a project grows on: a free starter template for AI-assisted development. One AGENTS.md every tool reads (Claude Code, Cursor, Grok Build, Codex, Gemini CLI, Copilot), TDD + bug-fix methodology, secret guardrails, optional local knowledge…
trellis copilot-instructions.md
Instructions for craigcossairt/trellis: Read and follow AGENTS.md at the repository root - it is the canonical instruction file for all AI agents on this project. Full methodology docs live in docs/methodology/: TDD workflow, bug-fix protocol, and session habits. Append bug patterns to docs/common-gotchas.md and…
trellis GEMINI.md
Instructions for craigcossairt/trellis: Read and follow AGENTS.md in this directory - it is the canonical instruction file for all AI agents on this project. Full methodology docs live in docs/methodology/.