From deep-loop
Stop ralph mode PRD processing. Use when user asks to 'cancel ralph', 'stop autonomous mode'. Halts background execution.
How this skill is triggered — by the user, by Claude, or both
Slash command
/deep-loop:cancel-ralphThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Stop ralph mode immediately by marking all PRD tasks as complete or deleting the PRD.
Stop ralph mode immediately by marking all PRD tasks as complete or deleting the PRD.
Check for PRD file at .deep/prd.json
Option A: Mark all complete (preserves history)
// For each task, set:
{
"passes": true,
"completedAt": "[timestamp]",
"skippedReason": "Cancelled by user"
}
Option B: Delete PRD (clean slate)
rm .deep/prd.json
Clean up state files
.deep/state.json to { "complete": true, "phase": "CANCELLED" }Confirm cancellation
Ralph mode cancelled. [N] tasks were pending.
PRD file: [preserved/deleted]
User: /cancel-ralph
Response:
Cancelling ralph mode...
Found 5 tasks in PRD:
- 2 completed
- 3 pending (now marked as skipped)
PRD preserved at .deep/prd.json with skip reasons.
State reset. You can now exit cleanly.
npx claudepluginhub marcusgoll/deep-loop-pluginProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
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.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.