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.
Borrowing it
Nothing to install: this file belongs to anthropics/launch-your-agent. 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/anthropics/launch-your-agent/main/CLAUDE.mdgit clone --depth 1 https://github.com/anthropics/launch-your-agentWrote 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/anthropics/launch-your-agent/claude-md)<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/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/anthropics/launch-your-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/anthropics/launch-your-agent/claude-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 | $0.02191 | $0.02191 |
| Opus 5.5 | $0.00876 | $0.00876 |
| Sonnet 5.5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
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 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.
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. 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. |
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 Changed a8168d76a6ab
- 2mo ago First seen · 39 lines · 2,191 tokens per session scan B ee7bed8a6531
launch-your-agent CLAUDE.md is an instructions file published in the GitHub repository anthropics/launch-your-agent (1,108 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,191 tokens to every session, about $0.0088 per session on Opus 5.5. 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.
launch-your-agent CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| launch-your-agent CLAUDE.mdanthropics/launch-your-agent | Instructions file | 1.1k | 1mo ago | Apache-2.0 | B | 2,191 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |