rome CLAUDE.md

rome CLAUDE.md is an instructions file for coding agents from rome-os/rome. It costs 1,210 tokens per session, scanned A, original, MIT.

A set of project instructions for Rome, a pnpm monorepo whose code is split across shared packages and runtime-loaded apps. A monorepo is one repository containing multiple related projects.

In plain words
What is it for?
Navigating Rome's backend, dashboard, UI kit, SDKs, desktop app, and plugin apps, then following the project's playbook for development and pull requests.
Why use it?
It gives coding agents the repository layout, dependency rules, and documentation checks they need before changing or explaining the code.

Instructions file

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/rome-os/rome/claude-md
Clone the repo
git clone --depth 1 https://github.com/rome-os/rome

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 rome CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rome-os/rome/claude-md.svg)](https://agentmods.dev/instructions/rome-os/rome/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rome-os/rome/claude-md"><img src="https://agentmods.dev/badge/instructions/rome-os/rome/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,210 This file is loaded in full into every session.
When invoked 1,210 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 $0.01210 $0.01210
Opus 5 $0.00605 $0.00605
Sonnet 5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured yesterday against content hash b5af0fe5874e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rome CLAUDE.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 yesterday.

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.

CLAUDE.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rome

A pnpm monorepo. All code lives under packages/* and rome_apps/*. Runtime dependencies are declared in packages/core — the root package.json holds only the dev toolchain, and its scripts delegate to the right workspace via pnpm --filter.

  • packages/core/ (@rome/core) — backend runtime: Hono server, agent/action/event subsystems, DB, channel adapters. src/index.ts wires the object graph via dependency injection.
  • packages/web/ (rome-web) — Rsbuild SPA dashboard, served by the backend. Guardian-only.
  • packages/ui/ (@rome-os/ui) — shared React component kit for the dashboard and apps.
  • packages/app-runtime-sdk/ (@rome-os/app-runtime) and packages/app-web-sdk/ (@rome-os/app-web-sdk) — SDKs consumed by apps.
  • packages/desktop/ (rome-desktop) — Electron shell.
  • packages/cdp-client/ (rome-cdp-client) — standalone CDP client.
  • rome_apps/* — runtime-loaded apps (plugins), each a workspace package.

Playbook

  • Before opening a PR, read docs/authoring/prs.md.
  • Before explaining a concept or asserting how a surface behaves, check docs/ and link instead of re-deriving.
  • Before building or editing an app, read rome_apps/CLAUDE.md.
  • When writing prose (docs, PR text), follow docs/authoring/WRITING.md.
  • When writing or editing code comments, follow docs/authoring/comments.md.
  • When a PR touches @rome-os/app-runtime, @rome-os/app-web-sdk, or @rome-os/ui, choose the Conventional Commit type by consumer impact. Test-only changes use test: and do not bump the package; releasable changes use feat: / fix: / feat!: (or BREAKING CHANGE: in the body). release-please publishes them to npm from Conventional Commits, with no per-PR changeset file. Full flow in docs/releases.md.
  • When running the fullstack local loop, use pnpm dev:all — containerized Rome with tsx --watch, plus rome-obs, Traefik, and the Rsbuild dev server. pnpm start and pnpm start:web skip the production-shaped wiring, so reach for them only to debug the host process.
  • When changing a file the container does not watch (package.json, container env), run docker compose restart <service>.
  • When doing frontend-only work in packages/web, use pnpm start:web:mock.
  • When verifying a change, run pnpm typecheck on the host, then pnpm test:unit, then pnpm dev:all and confirm the rome container reaches Rome started in docker logs. For UI changes, also exercise the feature in the browser — type checks and tests verify code correctness, not feature correctness.
  • When adding a runtime dependency, declare it in packages/core.
  • When bumping @playwright/test, re-pin the layout-invariants container image in .github/workflows/ci.yml to the matching release's digest (docker buildx imagetools inspect mcr.microsoft.com/playwright:v<version>-noble prints it). The image ships the browsers, the pin decides the client, and they are separate edits. Check the guard step's parse of playwright install --dry-run in the same pass, since it reads a CLI label that upstream can reword. The guard fails readably when the image and the client disagree.
  • When accessing the database, go through a repository. Core schema is packages/core/src/db/schema.ts, app schemas are rome_apps/*/db/schema.ts.
  • When adding config, validate it with Zod in packages/core/src/config.ts and add it to packages/core/.env.example.
  • When logging, use createLogger(component) from packages/core/src/logger.ts.

Read the full file on GitHub · 42 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. yesterday Changed · +1 lines · +4 tokens per session b5af0fe5874e
  2. 5d ago First seen · 41 lines · 1,206 tokens per session scan A e704af8de60c

Subscribe to this mod's changes

rome CLAUDE.md is an instructions file published in the GitHub repository rome-os/rome (471 stars, last pushed today), licensed MIT. It adds 1,210 tokens to every session, about $0.0060 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 2026-08-30.