agentmods.dev

rocketship: Instructions file for Claude Code

CLAUDE.md

rocketship CLAUDE.md is an instructions file for Claude Code from rocketship-ai/rocketship. It costs 4,210 tokens per session, scanned B, original, MIT.

Repository instructions for Rocketship, a cloud system that runs coding tasks across projects. They explain its current architecture, GitHub-based source control, project permissions, tokens, and support for monorepos.

In plain words
What is it for?
Use it when developing or configuring Rocketship’s engine, worker, control plane, project access, GitHub integration, or cloud execution workflow.
Why use it?
They give agents the project’s current rules for authentication, access control, uncommitted changes, and version compatibility. This helps avoid assumptions about how projects, users, and approvals work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is rocketship-ai/rocketship's own configuration. It tells Claude Code how to work on rocketship itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rocketship configures →

not rated 182repo 6mo ago B scan 4,210 tokens original MIT
View source ↗ rocketship-ai/rocketship docs.rocketship.sh
Reuse

Borrowing it

Nothing to install: this file belongs to rocketship-ai/rocketship. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rocketship-ai/rocketship/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rocketship-ai/rocketship

Made for: Claude Code.

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 rocketship CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rocketship-ai/rocketship/claude-md/github.svg)](https://agentmods.dev/instructions/rocketship-ai/rocketship/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rocketship-ai/rocketship/claude-md"><img src="https://agentmods.dev/badge/instructions/rocketship-ai/rocketship/claude-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.

agentmods 80×15 button for rocketship CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rocketship-ai/rocketship/claude-md"><img src="https://agentmods.dev/badge/instructions/rocketship-ai/rocketship/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,210 This file is loaded in full into every session.
When invoked 4,210 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.04210 $0.04210
Opus 5 $0.02105 $0.02105
Sonnet 5 $0.00842 $0.00842
Haiku 4.5 $0.00421 $0.00421

Measured 9d ago against content hash 6566c89f459a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

rocketship CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

echo "127.0.0.1 auth.minikube.local" | sudo tee -a /etc/hosts
CLAUDE.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Versioning note: Rocketship remains a v0 product. There are no backwards-compatibility guarantees. Remove or break legacy behaviours whenever it simplifies the current work, unless the user explicitly requests otherwise.

Rocketship Cloud v1 Snapshot (for agents)

  • Hosted experience uses GitHub device flow/OAuth via the controlplane; controlplane issues Rocketship JWTs checked by the engine. Engine, worker, Temporal remain the execution core.
  • Tenancy model is Org → Project (no workspaces). Projects capture repo URL, default branch, and path_scope globs to stay mono-repo friendly.
  • RBAC: project roles are Read and Write; Org Admins implicitly have Write everywhere. Tokens without role claims must be rejected.
  • Git-as-Source-of-Truth: UI/CLI can run uncommitted edits (labelled config_source=uncommitted). Rocketship helps users open PRs/commits but does not host approval workflows—everything merges in GitHub.
  • Tokens: user access/refresh pair (JWT + opaque refresh) plus per-project CI tokens with scopes and TTL. Engine annotates runs with initiator/environment/config source metadata for auditing.
  • Controlplane persists users/orgs in Postgres. Initial logins return pending roles until an org is created (POST /api/orgs) or the user is invited by an admin.
  • Guardrails & direction: enforce path scopes, deny unknown RPCs, keep minikube Helm flow as reference implementation.

Architecture Overview

Rocketship is an open-source testing framework for browser and API testing that uses Temporal for durable execution. The system is built with Go and follows a plugin-based architecture.

There are 3 "server" components that make up the Rocketship system: Temporal, Engine, and Worker. The CLI is meant to communicate with the engine. There are three ways to run Rocketship:

  1. Minikube stack with Skaffold (RECOMMENDED FOR AGENTS): scripts/setup-local-dev.sh + scripts/start-dev.sh provisions Temporal + Rocketship inside an isolated cluster with hot-reloading via Skaffold. Make code changes and watch them automatically rebuild and redeploy.
  2. Self-hosted cluster: Deploy the Helm charts to your own Kubernetes environment and connect the CLI remotely.
  3. Local processes: Use rocketship start server / rocketship run -af for quick experiments without Kubernetes.

Read the full file on GitHub · 479 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. 9d ago First seen · 479 lines · 4,210 tokens per session scan B 6566c89f459a

Subscribe to this mod's changes

rocketship CLAUDE.md is an instructions file published in the GitHub repository rocketship-ai/rocketship (182 stars, last pushed 6mo ago), licensed MIT. It adds 4,210 tokens to every session, about $0.0210 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agentse2e-testsgokubernetestemporal
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens