loop-factory
loop-factory is an agent skill published by juliusbrussee, listed under building agents. It lives in the JuliusBrussee/skills repository, which has 168 GitHub stars and is licensed under MIT; we last read it on 2026-09-16.
Runs a spec-driven agent loop where coding tasks are managed as markdown specs, transitioning through inbox → active → archive, implemented by Claude Code or Codex, and reviewed before completion. Requires no specific credentials.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads JuliusBrussee/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add JuliusBrussee/skills
What it connects to
Unverified means a mention in the skill’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.
Maintenance
Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count as done. Use when the user mentions "loop factory", a "spec-driven loop", an "agent factory", wants repeatable/reviewable agent work, or when a repo has a factory/specs/inbox or factory/specs/active directory. Also covers installing and scaffolding the loop-factory CLI into a project.
loop-factory compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| loop-factory (this page) | juliusbrussee | Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → arc… | 168 | 2026-08-07 |
| context-canary(same repository) | juliusbrussee | Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silen… | 168 | 2026-08-07 |
| deslopify(same repository) | juliusbrussee | De-slop pass for any text. Scans for the statistical fingerprints of AI writing (negative parallelism / "not… | 168 | 2026-08-07 |
| claude-handoff | mattpocock | Hand the current conversation off to a fresh background agent that picks up the work immediately. | 303,549 | 2026-10-22 |
| context-engineering | addyosmani | Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when swit… | 110,611 | 2026-10-13 |
| using-agent-skills | addyosmani | Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or wo… | 110,611 | 2026-10-13 |
| agent-platform-inference | Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemin… | 21,580 | 2026-10-25 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about loop-factory
- What does loop-factory do?
- Runs a spec-driven agent loop where coding tasks are managed as markdown specs, transitioning through inbox → active → archive, implemented by Claude Code or Codex, and reviewed before completion. Requires no specific credentials.
- How do I install loop-factory?
- Run npx skills add JuliusBrussee/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Which AI clients can use loop-factory?
- Its own description mentions Claude Code. That is a mention in its description, not a test we ran.
- Who publishes loop-factory?
- juliusbrussee.
- Is loop-factory maintained, and what licence does it use?
- Its repository has 168 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-08-07. The repository declares the MIT licence.
More agent skills for building agents
- python-sdkby 101-skills
- widgets-uiby 101-skills
- context-engineeringby addyosmani
- using-agent-skillsby addyosmani
- anti-detect-browserby antibrow
- browser-mcp-agentby antibrow