SuperAPI AI Directory

loop-factory

Agents & models

View repository

Updated 10-15 23:42

About this skill

Loop Factory

Use this skill to run spec-driven agent loops.

Workflow

  1. For new specs, use grill-me pattern before dispatch: ask one question at a time, provide recommended answer, and record final decisions in # Grill Gate.
  2. Inspect queue: python3 bin/loop-factory scan
  3. Choose one inbox spec unless user asks for batch work.
  4. Generate prompt: python3 bin/loop-factory dispatch --agent codex --limit 1
  5. If implementation starts, stage spec: python3 bin/loop-factory dispatch --agent codex --limit 1 --stage
  6. Implement only acceptance criteria.
  7. Run verification from spec frontmatter.
  8. Leave spec active for review.

Agent Use

For parallel work, explicitly ask Codex to spawn subagents. Use:

  • spec-implementer for scoped implementation
  • spec-reviewer for independent review
  • spec-backpropagator for spec/doc updates from diffs

Do not fan out same-file edits. Do not automate product choices. If spec is ambiguous, record assumption or open question.

Built-In Loops

Use repo-native loops when user asks for repeated work:

  • list: python3 bin/loop-factory loops list
  • inspect: python3 bin/loop-factory loops show <loop-id>
  • render: python3 bin/loop-factory loops prompt <loop-id> --agent codex

Prefer spec-grill-gate, active-spec-verify, independent-review-gate, and backprop-spec-sync for normal spec flow.

Outputs

Report:

  • spec id
  • files changed
  • verification commands and results
  • remaining risks
  • whether review/archive is ready