# Loop Factory

> Use when orchestrating Loop Factory specs from factory/specs/inbox or factory/specs/active, dispatching work, generating implementation prompts, or deciding next loop state.

- Skill: `juliusbrussee/loop-factory-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add juliusbrussee/loop-factory-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/juliusbrussee/loop-factory-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: Julius Brussee (https://skillmd.com/u/juliusbrussee)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/juliusbrussee/loop-factory-2

---


# Loop Factory

Run spec-driven agent loops.

## Current Queue

!`python3 bin/loop-factory scan`

## Workflow

0. 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`.
1. Pick one inbox spec unless user asks for batch.
2. Generate prompt:
   `python3 bin/loop-factory dispatch --agent claude --limit 1`
3. If implementation starts, stage spec:
   `python3 bin/loop-factory dispatch --agent claude --limit 1 --stage`
4. Implement acceptance criteria only.
5. Run verification from spec frontmatter.
6. Leave spec active for review.

## Autonomous mode (for `/loop`)

When driven by `/loop` (e.g. `/loop 30m /loop-factory`) or asked to run "autonomous"/"drain the inbox", do one self-contained pass with no human present:

1. `python3 bin/loop-factory scan` to see the inbox.
2. Build only **ready** specs — frontmatter `grill: completed`, or a filled `# Grill Gate`. Skip un-grilled specs and report them as "needs grilling". Never answer grill questions yourself.
3. For each ready spec: `python3 bin/loop-factory dispatch --agent claude --limit 1 --stage`, implement the acceptance criteria, run the spec's verification commands.
4. Leave built specs in `active/`. Do **not** archive — acceptance stays human.
5. If verification fails, leave the spec active with the failure noted; do not weaken criteria to pass.
6. If no ready specs, no-op and report an empty pass.

## Agent Use

Use project subagents when isolation helps:

- `spec-implementer`
- `spec-reviewer`
- `spec-backpropagator`

Use dynamic workflows only when many independent specs or cross-checks justify script-owned orchestration.

Do not automate product decisions. Record assumptions or open questions.

## 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 claude`

For interval loops, render prompt then use Claude Code `/loop <interval>` when appropriate.