Agent skill

looper-live-test

Run a live Looper smoke test by creating a temporary project (PROJECT.md + to-do.json), executing looper for one iteration, observing output, and reporting results. Use when verifying looper behavior or demonstrating a live run.

Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/looper-live-test

SKILL.md

Looper Live Test

Overview

Run a real looper iteration in a fresh temp directory to validate task selection and summary application, then report what happened.

Workflow

  1. Locate a looper.sh executable. Prefer looper.sh on PATH; otherwise set LOOPER_BIN to a specific path (for example ~/looper/bin/looper.sh).
  2. Run the helper script: ~/.codex/skills/looper-live-test/scripts/run-live-test.sh
  3. Watch the output until it finishes; note the Task: line and Summary: line.
  4. Inspect the temp project directory printed by the script; check to-do.json and any created files.
  5. Report: selected task line, summary line, files created, and any errors or unexpected behavior. Mention the temp dir path.

Manual fallback (only if the script cannot run)

  1. Create a temp directory and PROJECT.md.
  2. Create a to-do.json with tasks T10 and T2 (both priority 1).
  3. Run: CODEX_JSON_LOG=0 LOOPER_GIT_INIT=0 MAX_ITERATIONS=1 looper.sh to-do.json
  4. Observe output, then inspect to-do.json and created files.

Didn't find tool you were looking for?

Be as detailed as possible for better results