Cursor rule Cursor
Guard execution of approved plan/burndown work: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Apply to approved plan-.md, complete-everything, or burndown-full runs; binding for any implementation model.
Cursor rule Cursor
Skill routing where a name alone misleads: multi-phase requests, closure modes (complete-everything, burndown-full), and look-alike skills.
Cursor rule Cursor
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
Cursor rule Cursor
Require frontend changes and their DB/RPC/RLS/storage/secret dependencies to ship and be remotely verified together. Apply when implementing code that reads or writes backend state. Do not apply to plan- or present-then-stop audits; production data mutation still requires confirmation.
Cursor rule Cursor
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).
Cursor rule Cursor
Native Android (Kotlin/Java/Gradle) conventions.
Cursor rule Cursor
Native iOS conventions — verification is CI-only (no Mac locally).
Cursor rule Cursor
React Native JS/TS shared layer conventions.
Cursor rule Cursor
Web build conventions (separate from native and RN JS).
Cursor rule Cursor
Component patterns and UI conventions.
Cursor rule Cursor
Data fetching patterns with TanStack Query, Server Components, and Supabase.
Cursor rule Cursor
Git workflow and commit conventions.
Cursor rule Cursor
Supabase patterns and conventions for this project.
Cursor rule Cursor
Tailwind CSS and styling conventions.
Cursor rule Cursor
TypeScript conventions and type safety rules.
Cursor rule Cursor
Web performance guardrails (LCP priority, budgets, INP, bfcache) for Next.js/React app, page, and component files.
Cursor rule Claude CodeCursor
Senior-engineer execution defaults for the Next.js + React + Supabase stack — state/data library choices, separation of concerns, security non-negotiables. Attach when building or refactoring features in a React/Next.js/Supabase codebase.
Plugin Claude Code
Bundles 132 skills, 63 commands, 6 agents, 1 hook, 3 MCP servers · 9,491 tokens together
You say the job; the playbook runs. 157 agent skills, 63 slash commands, 6 subagents, and MCP templates for React / Next.js / Supabase. Effort-routed for Claude Opus 5.5: audit, plan, and judge skills at high, implementation at the medium default.
Cursor rule Claude CodeCursor
Guard execution of an approved plan or burndown: forbid reward hacking and feature deletion; require checkpoints, context discipline, safe terminal use, and fresh verification. Applies to approved plan-.md, complete-everything, and burndown-full runs, whatever model runs them.
Cursor rule Cursor
Search-tool fallback when Grep/Glob hang (>30 s on Windows hosts) or are unavailable — kill the PID, retry narrower, fall back to shell grep/ls/find.
Cursor rule Cursor
Mushi MCP safety and least-privilege rules for Cursor agents.
Plugin Claude Code
Bundles 1 agent · 79 tokens together
Triage and fix Mushi Mushi bug reports from inside Claude Code — reports, plain-English diagnosis, paste-ready fix context, optional fix dispatch.
Skill Claude CodeCodex
Set up and use Mushi Mushi, the bug mediator for AI-built apps: a user's bug report becomes a plain-English diagnosis and a paste-ready fix in Cursor or Claude Code over MCP. Use when installing the Mushi SDK, wiring the MCP server, managing Mushi keys, or asking how a Mushi feature works.
MCP server Claude CodeCodexCursor +2
The bug mediator for AI-built apps: plain-English diagnosis + a ready fix, in your editor. Runs locally from the @mushi-mushi/mcp npm package. Needs 4 environment variables to run.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: