What is agent-launcher-skills?

A plugin for building and running Claude Managed Agents through a staged workflow. It covers planning, launching, grading, improving, scheduling, and wrapping up, using generated scripts and configuration files.

Use it to interview for requirements, prepare a launch, run evaluation loops, deploy recurring jobs, and record the resulting agent setup.

It organizes the work into clear stages instead of treating agent creation as a single step. Bounded grading and deployment checks help prevent untested or unfinished workflows.

agent-launcher-skills — Plugin for Claude Code by alirezarezvani

About the project

claude-skills is a large collection of reusable skills, commands, plugins, and supporting resources for coding agents across engineering, business, research, compliance, and productivity work. It is used by people who want agents such as Claude Code, Codex, Gemini CLI, or Cursor to follow specialized workflows. The catalogue contains selected skills and settings from the collection.

alirezarezvani/claude-skills · 28,607 stars · on GitHub · alirezarezvani.medium.com

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.

Clone the repo

git clone --depth 1 https://github.com/alirezarezvani/claude-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/alirezarezvani/claude-skills/agent-launcher/github.svg)](https://agentmods.dev/plugins/alirezarezvani/claude-skills/agent-launcher)

Your own site

<a href="https://agentmods.dev/plugins/alirezarezvani/claude-skills/agent-launcher"><img src="https://agentmods.dev/badge/plugins/alirezarezvani/claude-skills/agent-launcher/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/alirezarezvani/claude-skills/agent-launcher"><img src="https://agentmods.dev/badge/plugins/alirezarezvani/claude-skills/agent-launcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 6 skills, 8 commands, 4 agents, 2 hooks cost 2,133 tokens a session between them.

Security scan A 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.

Security

Grade A, and why

agent-launcher-skills scanned grade A 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 today.

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.

Makes network callslowCapability

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

"description": "Turn Anthropic's launch-your-agent reference skill into a full domain plugin for building Claude Managed Agents (CMA). Every session starts with a goal (./my-agent/goal.json, surfaced by an opt-in AGENT_L

agent-launcher/.claude-plugin/plugin.json · 21 lines

How it starts

The opening of the file, as written. The whole thing — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "agent-launcher-skills",
  "description": "Turn Anthropic's launch-your-agent reference skill into a full domain plugin for building Claude Managed Agents (CMA). Every session starts with a goal (./my-agent/goal.json, surfaced by an opt-in AGENT_LAUNCHER_SESSION=1 SessionStart hook and driven by /cs-goal); a deterministic loop_compiler.py compiles that goal into a grade->iterate loop (CMA user.define_outcome self-grading, bounded by max_iterations), a recurring cron scheduled-deployment loop (run without you), or a single-pass interview->stage->launch workflow. 6 skills: agent-launcher-orchestrator (context: fork goal router) + interview (build sheet: primitives table + v1/v2 deferrals + eval plan) + stage-launch (validated env/agent/session/kickoff payloads + resumable BYOK curl launch script that never prints the key) + grade-iterate (outcome/rubric + verdict reader + held-back eval scaffold) + run-without-you (POSIX-cron deployment + NEXT-DIRECTIONS) + wrap-up (primitive inventory + regenerated overview HTML + next upgrades). 18 stdlib-only deterministic scaffolder tools (no network/API calls; live launches emitted as BYOK curl), 4 agents (orchestrator + interviewer + grader + deployer), 8 commands, opt-in SessionStart/SessionEnd hooks, 5 shared references, 4 assets. Validators enforce CMA limits (<=20 skills/session, <=8 memory stores, <=20 roster / 25 threads / depth-1 multiagent, max_iterations 1..20, <=20 creds/vault, <=1000 deployments/org). Inspired by anthropics/launch-your-agent (Apache-2.0); independent re-implementation, not a fork.",
  "version": "2.14.1",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/agent-launcher",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills/agent-launcher-orchestrator",
    "./skills/interview",
    "./skills/stage-launch",
    "./skil

Read the full file on GitHub · 21 lines

Contents

What it installs

The manifest is a name and a version. 6 skills, 8 commands, 4 agents, 2 hooks travel with it, and installing the plugin installs all of them — 2,133 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

authoring-notes.json 1.5 KB

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.

today First seen · 21 lines scan A 27570d679c15

Subscribe to this mod's changes

agent-launcher-skills is a plugin published in the GitHub repository alirezarezvani/claude-skills (28,607 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-24.

Building agents Planning agentic-ai anthropic-claude claude-ai claude-code-skills claude-skills

agent-launcher-skills

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Makes network callslowCapability

How it starts

What it installs

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

humanizer

claude-plugins-official marketplace

nextjs

themes-example

knowledge-work-plugins marketplace

superpowers