Agent Launcher Orchestrator

What it does

When your agent uses it

• A user wants to build
• Schedule a Claude Managed Agent (CMA) in their own Anthropic account — build me an agent
• Launch this as a managed agent
• Run this on a schedule

Example prompts

• “build me an agent”
• “launch this as a managed agent”
• “run this on a schedule”
• “/agent-launcher-orchestrator”

Requirements

• Python 3
• A credential in ANTHROPIC_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1No goal set. If goal.json is missing, run
2. 2Goal too vague. Router exit 4 — get one sentence naming the one job before
3. 3Never make API calls. Emit BYOK curl; the user runs it with their own
4. 4Never print the key. Launch scripts read the key from the environment.

What it can do on your machine

Read from SKILL.md and the folder at commit 19392f7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Launcher Orchestrator loads about 1.3k tokens when it runs. Until then it costs about 258 tokens; SKILL.md has 453 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~258

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from alirezarezvani/claude-skills at commit 19392f7, republished under its MIT licence (© alirezarezvani). 453 words, ~1,328 tokens.

name

agent-launcher-orchestrator

description

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).

context

fork

version

2.11.2

author

Alireza Rezvani

license

MIT

tags

claude-managed-agents, cma, agent, launch, orchestrator, session-goal, loop, workflow, cron, outcome, byok

compatible_tools

claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli

python3 scripts/goal_router.py --out-dir ./my-agent
# exit 0 ROUTE  -> fork to the named phase sub-skill
# exit 3 ASK    -> ask the one printed forcing question, then re-route
# exit 4 REFUSE -> goal too vague; get one sentence, then re-route

python3 scripts/loop_compiler.py \
  --out-dir ./my-agent --max-iterations 5 --cron "0 9 * * *" --timezone Europe/Berlin --nest-outcome

© alirezarezvani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts) in agent-launcher/skills/agent-launcher-orchestrator of alirezarezvani/claude-skills.

• SKILL.md
• README.md
• scripts/goal_router.py
• scripts/goal_state.py
• scripts/loop_compiler.py

Open the folder on GitHubat commit 19392f7