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
- Locate a
looper.shexecutable. Preferlooper.shon PATH; otherwise setLOOPER_BINto a specific path (for example~/looper/bin/looper.sh). - Run the helper script:
~/.codex/skills/looper-live-test/scripts/run-live-test.sh - Watch the output until it finishes; note the
Task:line andSummary:line. - Inspect the temp project directory printed by the script; check
to-do.jsonand any created files. - 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)
- Create a temp directory and
PROJECT.md. - Create a
to-do.jsonwith tasksT10andT2(both priority 1). - Run:
CODEX_JSON_LOG=0 LOOPER_GIT_INIT=0 MAX_ITERATIONS=1 looper.sh to-do.json - Observe output, then inspect
to-do.jsonand created files.
Didn't find tool you were looking for?