Cursor rule Cursor
Agent-run verdict workflow for contract wiring, backend enrichment, workflow panels, exact verdicts, and verification.
not rated 15
+1 today A 449 tokens
original MIT
Cursor rule Cursor
Agentic Systems Reliability — 8-point checklist for agent-facing infrastructure.
not rated 15
+1 today A 513 tokens
original MIT
Cursor rule Cursor
Root-cause diagnosis over bandaid fixes — trace upstream before writing code.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
When completing any task (step, feature, fix, plan), always cite back to the user's original request.
not rated 15
+1 today A 0 tokens
original MIT
convex_rules
05Cursor rule Cursor
Guidelines and best practices for building Convex projects, including database schema design, queries, mutations, and real-world examples.
not rated 15
+1 today A 4,645 tokens
original MIT
Cursor rule Cursor
Deep-read audit protocol — full end-to-end reads only, parallel subagents, numbered findings.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
Every UI change MUST be visually verified in the running app before declaring done. Code-level changes without visual confirmation are unverified assumptions. But verification is not just "does it render?" — it's "does it belong?".
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
When in flywheel mode, operate as a continuous improvement loop.
not rated 15
+1 today A 409 tokens
original MIT
Cursor rule Claude CodeCursor
Cursor rule "forecasting_os" from HomenShum/NodeBenchAI, covering forecasting os, architecture, three surfaces, one data spine, cross-reference engine (deterministic, no llm) and trace wrapping.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Claude CodeCursor needs its repo
Continuous dogfood loop using Gemini 3 Flash vision to score and fix UI/UX issues automatically.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
Owner-mode end-to-end workflow for finishing contract, backend, UI, exact status, verification, and workflow documentation.
not rated 15
+1 today A 245 tokens
original MIT
Cursor rule Cursor
Ship quality is proven in the running UI, not in a diff.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
Re-examine accessibility — ARIA, reduced motion, color-blind safety, screen readers, focus management.
not rated 15
+1 today A 452 tokens
original MIT
Cursor rule Claude CodeCursor
Every element must earn its place. The default answer to "should we add this?" is no. Reduction is not simplification — it's the discipline to remove everything that doesn't serve the user's immediate task.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
Re-examine keyboard efficiency — skip links, shortcuts, tab order, focus traps.
not rated 15
+1 today A 411 tokens
original MIT
Cursor rule Cursor
Re-examine performance — progressive disclosure, deferred rendering, smart refresh, lazy loading.
not rated 15
+1 today A 417 tokens
original MIT
Cursor rule Cursor
Re-examine visual polish — skeleton loading, staggered animations, transitions, micro-interactions.
not rated 15
+1 today A 465 tokens
original MIT
Cursor rule Cursor
Re-examine for 11/10 — the fresh-eyes quality pass after completing any non-trivial work.
not rated 15
+1 today A 402 tokens
original MIT
Cursor rule Cursor
Re-examine error resilience — retry with backoff, partial failures, error boundaries, graceful degradation.
not rated 15
+1 today A 373 tokens
original MIT
Cursor rule Cursor
Scenario-based testing mandate — no shallow tests, real human behavior, scale + duration axes.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
Self-direction — never wait, decide and act immediately.
not rated 15
+1 today A 221 tokens
original MIT
Cursor rule Cursor
Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, parallel code reviews, pipeline workflows, or self-organizing task queues.
not rated 15
+1 today A 37 tokens
original MIT
nodebench
23MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
Turn messy input into a sourced report. 15 default tools: workflow, bidirectional sync, canonical NodeBench research bridge, discovertools, and loadtoolset. Runs locally from the nodebench-mcp npm package.
not rated 15
+1 today A
tokens not measured
original MIT
ta-studio
24MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
TA Studio MCP server for Claude Code — AI-powered QA automation. Runs locally from the ta-studio-mcp npm package. Needs 2 environment variables to run.
not rated 15
+1 today A
tokens not measured
original MIT
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: