Loopy
Designs, finds, audits and runs bounded AI-agent loops with evidence receipts, backed by a live Loop Library catalog.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 10, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 18, 2026 · 5fe3082
Ran the real 'Find a published loop' workflow against the live catalog.json (85 real entries, fetched from signals.forwardfuture.com) for a flaky-CI-test scenario and it surfaced loop #044 'The test stabilizer loop' with an almost verbatim useWhen match, exact URL and author — a baseline answer without the skill would have had to invent or hand-wave a recommendation instead of grounding it in real, live data.
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 9/10
- Docs & honesty 5/5
What Loopy does
A large workflow skill for treating AI-agent automation as bounded, verifiable 'loops' with explicit stopping conditions instead of open-ended autonomy: discover recurring work from a codebase or thread history, find or adapt a match from the live Forward Future Loop Library catalog, audit/repair an existing loop, craft one through a short interview, run it and return an evidence receipt, debrief a completed run, or save/publish a loop. Triggers on requests to design, review, or execute a repeatable agent workflow with a defined success/stop condition; does not trigger for a plain programming for-loop or a generic cron/scheduling request.
How to install Loopy
git clone https://github.com/Forward-Future/loopy
cd loopy
mkdir -p ~/.claude/skills
cp -r skills/loopy ~/.claude/skills/loopy
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Loopy
-
/loopyDesigns, finds, audits and runs bounded AI-agent loops with evidence receipts, backed by a live Loop Library catalog.
It also activates on plain-language prompts like these:
-
Design a bounded agent loop with a clear stop condition -
Find a matching loop in the Loop Library for this workflow -
Audit and repair my existing agent loop's evidence receipts
Frequently asked questions
- Is the Loopy skill free?
- Yes. The skill itself is free from Forward-Future/loopy. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Loopy work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 10, 2026. Verdict: Tested · Works. Ran the real 'Find a published loop' workflow against the live catalog.json (85 real entries, fetched from signals.forwardfuture.com) for a flaky-CI-test scenario and it surfaced loop #044 'The test stabilizer loop' with an almost verbatim useWhen match, exact URL and author — a baseline answer without the skill would have had to invent or hand-wave a recommendation instead of grounding it in real, live data.
- What is the Loopy SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Loopy?
- 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 Loopy 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.