Command Claude Code
Stress-test limps CLI, MCP, and HTTP server for robustness, prompt-injection, and safety.
limps your Local Intelligent MCP Planning Server across AI assistants. No subscriptions, no cloud—run it locally. Version control your planning docs in git. No more context drift—one shared source of truth across Claude, Cursor, Copilot, and any MCP tool.
Command Claude Code
Stress-test limps CLI, MCP, and HTTP server for robustness, prompt-injection, and safety.
Command Claude Code
Run a product-manager-style audit of a feature plan: scorecard by category, findings by severity, duplicate-feature detection across plans, and concrete next edits. Use after creating or updating a plan and before running agents; output is intended to feed back into the plan for iterative improvement.
Command Claude Code
Verify agent completion, sync status, and identify unblocked work.
Command Claude Code
Generate a TDD plan with verbose planning docs and minimal agent execution files using MCP planning tools.
Command Claude Code
List all available feature plans with their work types, names, and overviews.
Command Claude Code
Simple entry point: "I want to check plan status". Shows plan status without overwhelming detail.
Command Claude Code
List all agents in a plan with their status, features, and clickable links. Helps you find and select which specific agent to run.
Command Claude Code
Triage failing PR checks and apply fixes using limps workflows and scripts only.
Command Claude Code
Fetch, review, address, and resolve unresolved PR review comments using the scripts/helpers/pr-comments.ts helper.
Command Claude Code
Create a PR on GitHub with a limps-aware description based on staged changes or recent commits.
Command Claude Code
Review changes on the current branch compared to main.
Command Claude Code
Run the MCP/LLM-focused review skill for this repo.
Command Claude Code
Select the next best agent task from a plan and open it in Cursor, or run a specific agent file.
Command Claude Code
Apply feedback to an existing plan, regenerate affected agent files, and commit after approval.