Use agent-loop-design

Design a supervised agent loop

Design a supervised agent loop — the generate→verify→gate cycle, observable exit criteria, hard iteration cap, human gates at irreversible steps, and failure routes — as a loop spec a team can implement in any agent harness.

Reach for it when the user wants to automate a recurring task with an AI agent loop, design a work loop / review loop / research loop, or asks "how do I stop my agent from running forever or shipping junk".

Install it

npx skilldrop-cli install agent-loop-design                 # Claude Code, your user folder
npx skilldrop-cli install agent-loop-design --project       # Claude Code, this repo
npx skilldrop-cli install agent-loop-design --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the AI engineering pack: --pack ai-engineering installs it with its neighbours.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "Design an agent loop to keep our runbooks up to date"
• "My agent keeps iterating forever — how do I add proper exit criteria?"
• "Turn this prompt we run by hand every week into a supervised automation loop"
• "Review this proposed agent automation for missing human gates"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Implement this user story with tests"
• "Split this task across parallel subagents"
• "How many tokens should this workflow be allowed to spend?"

If another skill answers instead, ask for this one by name: "use agent-loop-design".

Check what you get

A good result:

• The done-condition is observable — a person who didn't watch the run can check it in minutes.
• Verifier ≠ generator, structurally: different persona, prompt, or program — stated in the spec, not implied.
• Both caps are numbers. "Reasonable number of iterations" is not a cap; 3 is.
• Every irreversible action has a human gate, and every gate has a decision-shaped digest format.
• Generate consumes findings. The spec shows the findings flowing into the next round's input.
• All three failure routes are specified — cap-hit, can't-judge, systemic — each with a destination.
• The Mermaid renders and contains only generate/verify/gate states plus the human-gate and escalate exits — no "polish"/"reflect" states without a verdict.

Use something else when

• Implementing one feature right now — run feature-implement-loop; it is the loop
• Splitting one task across parallel agents — subagent-design
• Deciding what the loop may spend — agent-budget
• One-off tasks — a loop for something that runs once is ceremony

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: agent-budget, devils-advocate, feature-implement-loop, llm-eval-harness, subagent-design

Edit this page on GitHub · View source