Don't Stop
Drive authorized implementation tasks through testing, self-repair, and evidence-backed delivery.
Free
Works with the AI Agents you already use
About this skill
Don't Stop is an autonomous completion-loop skill for Codex and compatible agent-skill runtimes. It guides authorized implementation work through inspecting current project state, defining acceptance criteria, implementing changes, running applicable checks, repairing recoverable failures, reviewing the result, and delivering verification evidence.
For multi-phase or long-running tasks, it maintains compact checkpoints and records action outcomes to support safe resumption without repeating completed work. Verification scales to the task: focused checks, regression tests, builds, artifact inspection, and real user-facing or external-state checks when applicable and available.
The skill preserves the user's authorization boundaries. It does not independently authorize production publishing, destructive changes, payments, external messages, or other actions outside the requested scope. It pauses for genuine blockers such as authentication, missing credentials, or decisions requiring the user.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Instruction-based workflow guidance, not a guarantee that every task can be completed. It cannot supply missing credentials, tools, services, or authorization. Not intended for exploration-only, plan-only, review-only, diagnosis-only, status, or explanation requests that do not authorize changes.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 25 days ago
- Free with an Agensi account
- Software
Git