Loop Maker
Turns a one-line idea into a safe, self-verifying autonomous-agent mission prompt
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 18, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · 193d5f3
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Asked both to write a build-and-test prompt for a coffee-shop landing page: the bare baseline said only 'test it', which an agent can loop on forever or fake, while the skill's Mission Card pinned a provable stop condition, a turn cap, a verifier separate from the writer, and no-deploy/no-spend guardrails. Its seven reference and template files all load, and the install ran verbatim from a bare HOME.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Loop Maker does
Interviews you briefly, then engineers a complete mission prompt for an autonomous coding agent: a pinned spec, a verifier that is not the writer, and a provable stop condition with a turn/time cap. Triggers on phrasings like 'make me a loop', 'write me a prompt', 'run this overnight', or 'ship while I sleep'; ships a copy-paste Mission Card or a full BUILD-LOOP scaffold.
How to install Loop Maker
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Loop Maker
-
/loop-makerTurns a one-line idea into a safe, self-verifying autonomous-agent mission prompt
It also activates on plain-language prompts like these:
-
Make me a loop that builds and tests this landing page overnight. -
Write me a prompt so an agent can ship this feature while I sleep. -
Help me plan this feature so an autonomous agent can build it safely.
Frequently asked questions
- Is the Loop Maker skill free?
- Yes. The skill itself is free from jbrazy480/loop-maker. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Loop Maker work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Tested · Works. Asked both to write a build-and-test prompt for a coffee-shop landing page: the bare baseline said only 'test it', which an agent can loop on forever or fake, while the skill's Mission Card pinned a provable stop condition, a turn cap, a verifier separate from the writer, and no-deploy/no-spend guardrails. Its seven reference and template files all load, and the install ran verbatim from a bare HOME.
- What is the Loop Maker SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Loop Maker?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Loop Maker with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.