Detect when an agent is looping or failing repeatedly, and trigger structured recovery — backtrack, simplify, or escalate.
From devkitnpx claudepluginhub 5uck1ess/devkitThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
You are stuck if any of these are true:
Read .devkit/scratchpads/current.md first. It records what was already tried and why it failed. If the scratchpad shows 3+ failed iterations, skip straight to Step 5: Escalate — the pattern of failures is the diagnosis.
Don't retry the same approach. Read the error carefully:
If the last 2+ attempts failed:
git checkout -- .Reduce scope:
If the same approach failed twice:
If you've tried 3+ different approaches: