sebastienrousseau/agtmls/agent-loop-design
Claude Code and agent skill by sebastienrousseau/agtmls
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Use when turning repeated agent work into a loop with trigger conditions, evidence, stopping criteria, uninstall state, validation checks, and reviewable artifacts.
Install
npx vskill@latest install sebastienrousseau/agtmls/agent-loop-designSKILL.md
Agent Loop Design
Use this skill to design repeatable agent workflows that can run manually, on a schedule, or from a hook.
Workflow
- Define the trigger: manual, file change, schedule, failed check, or user phrase.
- Define scope, permissions, and stopping criteria before execution.
- Record evidence: inputs, commands, files touched, outputs, and verification.
- Make installation reversible with a manifest of every path created.
- Add a dry-run path and at least one smoke test.
- Promote the loop only after it passes validation and a human review gate.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/agent-loop-design/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/sebastienrousseau/agtmls/agent-loop-design)