🔓 unclaimed — this page was auto-generated from GitHub. Are you the creator?
Claim this page →
loop-maker
Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenClaw).
git clone https://github.com/EricTechPro/loop-maker
loop-maker
A portable agent skill — works in Claude Code, Codex, Hermes, and OpenClaw — that interviews you and scaffolds a self-running autonomous loop, complete with verifier, state file, and human gate, so you don't build one wrong.
Why most loops go wrong
- Forgot to write a separate verifier (the agent judged its own work)
- Leaked changing state into the skill file (the loop lost memory between runs)
- Shipped a loop with no stop condition (it ran forever and burned budget)
loop-maker catches all three before you write a line.
Here's what it'll ask you
🛠 To build a loop, it asks you 7 things — one at a time:
1. Goal — what checkable condition means "done for now"? (a true/false test, not a vibe)
2. Trigger — what starts each run: a schedule, an event, or run-until-done?
3. Discovery — how does it find the work to do each round?
4. Action — what's it allowed to do, and through which tools?
5. Verification— who checks the result, and against what? (a separate judge)
6. State — where does "what's done / what's left" live, outside the chat?
7. Human gate — which actions are irreversible and must ask you first?
At a glance
| What it does | Runs a 7-question wizard; catches missing verifiers, state leaks, and runaway loops before scaffold |
| What you get | A ready-to-run loop folder: SKILL.md + STATE.md + verifier script + stop condition wired in |
| How you start | /loop-maker, or just describe an automate/schedule/monitor task — fires without the word "loop" |
| Install | git clone … ~/.claude/skills/loop-maker — or see Install below |
Wizard UX
Q3/7 ▓▓▓░░░░ 43%
---
🎙 elicit → 🔎 survey → 🎯 select → 🏗 scaffold
(you are here: 🎯 select)
---
┌─ LOOP BLUEPRINT ───────────────────────────────────┐
│ GOAL ✓ verifiable │
│ TRIGGER schedule · 08:00 │
│ VERIFY ✓ separate script │
│ STATE loops/<name>/STATE.md │
│ GATES merge = human · budget 25/run │
└────────────────────────────────────────────────────┘
The progress bar, breadcrumb, and blueprint box are rendered live by scripts/loop_progress.py — a zero-dep Python 3 helper that ships with the skill.
Flow
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ elicit │────▶│ survey │────▶│ select │────▶│ scaffold │
│ 7 Qs │ │ gap │ │ confirm │ │ write │
│ one-by │ │ check │ │ loop │ │ files │
│ one │ │ + warn │ │ shape │ │ + test │
└──────────┘ └──────────┘ └──────────┘ └──────────┘
│ │ │
progress bar flags leaky human reviews loop ready
Qx/7 rendered state / missing blueprint box to invoke
verifier / no stop
Install
# Option A — drop into your global Claude skills folder
git clone https://github.com/EricTechPro/loop-maker ~/.claude/skills/loop-maker
# Option B — install into a custom skills directory
LOOP_MAKER_SKILLS_DIR=~/my-project/.claude/skills ./install.sh
Usage
/loop-maker
That's it. The wizard runs, asks 7 questions, and writes the scaffolded loop under loops/<name>/ in your project.
What this is NOT
- Not a runtime.
loop-makerscaffolds loops; it doesn't execute them. Your loop runs as a separate Claude Code skill or cron job. - Not a single-purpose tool. It works for any autonomous loop — content pipelines, monitoring agents, data-sync jobs, outreach sequences — not one niche use case.
- Not a free pass on the human gate. Question 7 is non-skippable. If an action is irreversible, the scaffold will wire in an approval step — no override.
License
MIT © Eric Tech. See LICENSE.
Credits
Designed and maintained by Eric Tech.
Further reading: Addy Osmani on agent design patterns; Anthropic's documentation on agentic loops and tool use.
// compatibility
| Platforms | cli |
|---|---|
| Operating systems | — |
| AI compatibility | claude |
| License | MIT |
| Pricing | open-source |
| Language | Go Template |
// faq
What is loop-maker?
Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenClaw).. It is open-source on GitHub.
Is loop-maker free to use?
loop-maker is open-source under the MIT license, so it is free to use.
What category does loop-maker belong to?
loop-maker is listed under automation in the Claudeers registry of Claude-compatible tools.
// embed badge
[](https://claudeers.com/loop-maker)
// retro hit counter
[](https://claudeers.com/loop-maker)
// reviews
// guestbook
// related in Claude Skills
🔓An agentic skills framework & software development methodology that works.
🔓
🔓💫 Toolkit to help you get started with Spec-Driven Development
🔓AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs,…