auto-skill-build-supercharge-feedback-loop

name

auto-skill-build-supercharge-feedback-loop

description

Run closed-loop evaluators for Codex Supercharge artifacts and write feedback state for future Codex sessions, subagents, and automations. Use after creating, editing, reviewing, grading, or validating Codex Supercharge skills, references, scripts, metadata, or public docs. Triggers: grade Supercharge edits, closed-loop feedback, evaluator handoff, subagent status, automation feedback. Skip when the task is a one-off repo edit outside Codex Supercharge.

Supercharge Feedback Loop

Generated by: Codex Supercharge maintenance automation.

Goal: make every meaningful Codex Supercharge create/edit/review leave a graded artifact trail and a compact handoff for the next agent or automation.

Workflow

1. After changing or reviewing pack artifacts, run the feedback evaluator on the changed files or the full pack.
2. Include the task, action, validation commands, and concise notes.
3. Read .agent-runs/supercharge-status.md before future Supercharge work.
4. Promote repeated feedback items into helper fixtures, skill audit checks, or public-readiness gates.
5. Keep feedback state local under .agent-runs/; public export helpers exclude it by design.

Commands

python3 plugins/codex-supercharge/scripts/supercharge_feedback.py evaluate \
  --plugin-root plugins/codex-supercharge \
  --task "Describe this Supercharge change" \
  --action edited \
  --artifact plugins/codex-supercharge/skills/example/SKILL.md \
  --command "make -C plugins/codex-supercharge ci" \
  --note "What changed and what remains"

python3 plugins/codex-supercharge/scripts/supercharge_feedback.py report \
  --runs-dir plugins/codex-supercharge/.agent-runs \
  --last 5

For a broad sweep, omit --artifact; the evaluator scans skills, references, scripts, metadata, and public docs.

Skip When

• The work is unrelated to plugins/codex-supercharge.
• The repo is too sensitive to persist local feedback state.
• You need hosted production traces, gateways, canaries, or live guardrails; use $auto-skill-build-agent-reliability-loop.

References

• plugins/codex-supercharge/references/supercharge-feedback-loop.md
• plugins/codex-supercharge/references/agent-run-ledger.md
• plugins/codex-supercharge/references/future-agi-agent-reliability-loop.md

Validation

python3 plugins/codex-supercharge/scripts/supercharge_feedback.py evaluate \
  --plugin-root plugins/codex-supercharge \
  --runs-dir /tmp/codex-supercharge-feedback-smoke \
  --task "feedback smoke" \
  --artifact plugins/codex-supercharge/skills/auto-skill-build-supercharge-feedback-loop/SKILL.md

python3 "$HOME/.codex/skills/.system/skill-creator/scripts/quick_validate.py" \
  plugins/codex-supercharge/skills/auto-skill-build-supercharge-feedback-loop

The feedback run should append one JSONL batch and refresh supercharge-status.md plus evals.md.