- name
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"
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill agent-launcher-orchestrator -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill agent-launcher-orchestrator -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill agent-launcher-orchestrator -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill agent-launcher-orchestrator -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/alirezarezvani/claude-skills/tree/HEAD/.gemini/skills/agent-launcher-orchestratorFrom the publisher
Every session starts with a goal — one sentence for one CMA. This orchestrator reads that goal, routes to the right phase, and compiles the goal into a loop or a workflow. Heavy intake stays in the forked context; the parent gets a digest.
Inspired by Anthropic's launch-your-agent reference skill (Apache-2.0). This is
an independent re-implementation; CMA semantics come from
../../references/cma-primitives.md.
State lives at ./my-agent/goal.json (the user's folder). Manage it with
goal_state.py (init / set / status / advance) — it also backs the /cs:goal
command and the opt-in SessionStart hook. The goal's phase selects the lane;
the phase + recurrence selects the loop shape.
Run the router, then act on its exit code:
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
loop_compiler.py emits plan.v1: single-pass, grade-iterate (always with a
max_iterations cap 1..20), or cron-loop (optionally nesting a self-grading
outcome per firing). See ../../references/loops-and-workflows.md.
goal.json is missing, run
goal_state.py init --goal "..." first. The orchestrator does not guess a goal.$ANTHROPIC_API_KEY. No script in this plugin touches the network.After routing, fork to the sub-skill with: the goal string, agent_name,
out_dir (./my-agent), and the compiled plan.v1. When the sub-skill returns,
goal_state.py advance moves the phase and the parent gets a ≤100-word digest
(phase done, artifact paths, loop shape, one next step).
./my-agent-*/ folders.scripts/goal_state.py — own goal.json (init/set/status/advance).scripts/goal_router.py — goal → lane (exit 0 route / 3 ask / 4 refuse).scripts/loop_compiler.py — goal+phase → plan.v1 execution shape.© 2026 Skills Rack.
---name: agent-launcher-orchestratordescription: Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic…---# .gemini/skills/agent-launcher-orchestrator/SKILL.mdOverview
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).
FAQ
Download .gemini/skills/agent-launcher-orchestrator/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/alirezarezvani/claude-skills.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.