launch-your-agent CLAUDE.md

launch-your-agent CLAUDE.md is an instructions file for coding agents from anthropics/launch-your-agent. It costs 2,191 tokens per session, scanned B, original, Apache-2.0.

A project guide and skill for building and launching agents on Claude Managed Agents, Anthropic’s hosted agent service. It covers the process from defining an initial version to testing and improving it.

In plain words
What is it for?
Planning an agent, preparing its build, launching it, evaluating its results, iterating on later versions, and scheduling it to run automatically.
Why use it?
It gives technical founders a structured way to turn an idea into a launched agent and decide what to improve next.

Instructions file

About the project

Launch Your Agent is a Claude Code skill that guides a founder through building and deploying a managed agent in their own Claude account. It interviews the user, defines an initial version, launches and evaluates it, then helps iterate or schedule it. The catalogue skills provide this guided workflow.

anthropics/launch-your-agent · 980 stars · on GitHub

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/anthropics/launch-your-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/anthropics/launch-your-agent

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 launch-your-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anthropics/launch-your-agent/claude-md.svg)](https://agentmods.dev/instructions/anthropics/launch-your-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/anthropics/launch-your-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/anthropics/launch-your-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,191 This file is loaded in full into every session.
When invoked 2,191 The same file — it is already loaded in full.
Security scan B 2 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 $0.02191 $0.02191
Opus 5 $0.01095 $0.01095
Sonnet 5 $0.00438 $0.00438
Haiku 4.5 $0.00219 $0.00219

Measured 5d ago against content hash ee7bed8a6531, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

launch-your-agent CLAUDE.md scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

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

- **Never stop to wait for the key — heads-up early, hand over late**: as soon as a credential is inevitable (API key, connector token/webhook), tell the founder where to get it (a "grab these while I stage" table rides

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Audience: technical founder, self-directed, inside Claude Code. Show the machinery (curl/`ant`), don't hide it.
CLAUDE.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cma-test — "launch your managed agent" skill

What this project is

A Claude Code skill (launch-your-agent) that helps a technical founder build whatever they want on Claude Managed Agents (CMA) — an internal worker, a piece of their product, a customer-facing agent; recurring or one-off: interview → build kit → launch → eval → iterate → scheduled deployment (when it should run on a clock). General-purpose, not a workshop — no clock/"hour" framing, no "recurring task" requirement; the spine is an iterative lens (scope a v0, launch and grade it, layer upgrades as v1/v2 via NEXT-DIRECTIONS).

Repo map (state as of 2026-06-15)

Path What it is
cma-primitives.md Full inventory of CMA primitives/limits from the live docs (incl. scheduled deployments at /managed-agents/scheduled-deployments)
.claude/skills/launch-your-agent/references/examples-bank.md Sourced-only archetypes (each traced to an official cookbook/doc), production proof-point links, §5 = other-ideas backlog
ui/agent-overview-example.html + ui/overview.css + ui/build-sheet.example.json The overview page example (live-schema dashboard, kept identical to the skill's overview-template.html + overview.css) + example build sheet — open locally in a browser
.claude/skills/launch-your-agent/ The skill: SKILL.md (4 phases) + references/ (interview, cma-api, examples-bank, overview-template + overview.css, build-sheet example). Also installed at ~/.claude/skills/launch-your-agent/ for testing — keep both copies in sync (repo is the source of truth).
.claude/skills/wrap-up/ Companion skill /wrap-up: owns the close-out / status check for a built agent (overview refresh, primitives recap, run log, tailored extensions, hygiene sweep). Reuses launch-your-agent's references via ../launch-your-agent/references/. Installed at ~/.claude/skills/wrap-up/. launch-your-agent's Phase 4 invokes it.

Read the full file on GitHub · 39 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 · 39 lines · 2,191 tokens per session scan B ee7bed8a6531

Subscribe to this mod's changes

launch-your-agent CLAUDE.md is an instructions file published in the GitHub repository anthropics/launch-your-agent (980 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,191 tokens to every session, about $0.0110 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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 · 3,733 tokens