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-grade.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

1.2 KiB
Raw Permalink Blame History

description argument-hint
Phase 3 — the bounded grade→iterate loop. Define a CMA outcome (required rubric, max_iterations 1..20), read each grader verdict, decide the next move, and run held-back eval cases once a version passes, via the grade-iterate skill. Never unbounded. [optional: path to build-sheet.json]

/cs:grade — Phase 3: Grade → Iterate

Run the grade-iterate skill.

$ARGUMENTS

Steps

  1. python3 agent-launcher/skills/grade-iterate/scripts/outcome_builder.py --sheet ./my-agent/build-sheet.json --max-iterations 5 --out ./my-agent/payloads/outcome.json — rubric required; send as a user.define_outcome event.
  2. On each verdict: python3 agent-launcher/skills/grade-iterate/scripts/verdict_reader.py --result ./my-agent/last-verdict.json → SHIP / SHARPEN / ESCALATE / RESUME. Each iteration must move ≥1 rubric line fail→pass.
  3. Once a version passes: python3 agent-launcher/skills/grade-iterate/scripts/eval_scaffold.py --sheet ./my-agent/build-sheet.json --out ./my-agent/eval.json — held-back cases in parallel (≤25 threads).
  4. Decide: ship v0, or goal_state.py set --phase run-without-you.

Bounded loops only. Read the verdict before acting. Held-back cases stay held back.