scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-10-08 03:07:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/agent-launcher/commands/cs-goal.md
Claude d1f2396c6f
feat(agent-launcher): new domain plugin for building Claude Managed Agents 
Adds the agent-launcher/ top-level domain — a plugin re-implementation of
Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a
fork) for building Claude Managed Agents (CMA) in the user's own account.

Every session starts with a goal (./my-agent/goal.json, surfaced by an opt-in
AGENT_LAUNCHER_SESSION=1 SessionStart hook + /cs:goal); loop_compiler.py
compiles that goal into a bounded grade->iterate loop (CMA user.define_outcome
self-grading, max_iterations 1..20), a recurring POSIX-cron scheduled-deployment
loop, or a single-pass interview->stage->launch workflow.

- 6 skills: agent-launcher-orchestrator (context: fork goal router) + interview
  + stage-launch + grade-iterate + run-without-you + wrap-up
- 18 stdlib-only deterministic scaffolder tools (NO network/API calls; live
  launches emitted as BYOK curl that never prints the key); all pass --help/--sample
- 4 agents (orchestrator + interviewer + grader + deployer), 8 /cs:* commands
- opt-in SessionStart/SessionEnd hooks (exit 0 on any error), 5 shared
  references, 4 assets (build-sheet schema + overview/next-directions templates
  + example)
- validators enforce CMA limits (<=20 skills/session, <=8 memory stores,
  depth-1 multiagent, max_iterations <=20, <=1000 deployments/org)
- registered in marketplace.json; headline counters trued up via
  derive_counters.py --check (skills 362->368, domains 18->19, tools 644->664,
  refs 741->746, agents 102->106, commands 116->124, plugins 88->89)

Distinct from engineering/agent-harness (generic bounded loop over any domain)
and engineering/write-a-skill (authors Claude Code skills, not CMAs).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012FwXG6TqCXKZQvF4iD69cv
2026-08-17 02:39:34 +00:00

1 KiB
Raw Permalink Blame History

description argument-hint
Set, show, or advance the per-session agent-launcher goal (./my-agent/goal.json) — the through-line of a CMA launch. Backs the opt-in SessionStart hook. Subcommands map to goal_state.py init/set/status/advance. set "<goal>" | status | advance | phase <name>

/cs:goal — manage the session goal

The goal is one sentence for one agent. It selects the phase and the loop shape.

$ARGUMENTS

Run goal_state.py under agent-launcher/skills/agent-launcher-orchestrator/scripts/:

  • set "<goal>" → goal_state.py init --goal "<goal>" (or set --goal if it exists).
  • status → goal_state.py status (prints goal, agent_name, phase, phases_done, loop).
  • advance → goal_state.py advance (moves to the next phase).
  • phase <name> → goal_state.py set --phase <name> (interview | stage-launch | grade-iterate | run-without-you | wrap-up | done).

Enable auto-surfacing each session with export AGENT_LAUNCHER_SESSION=1 (the opt-in SessionStart hook). Two jobs → two goals in two ./my-agent-*/ folders.