codegraph
49Cursor rule Cursor
CodeGraph MCP usage guide — when to use which tool.
not rated 9 2mo ago A 762 tokens
original MIT
ctx
50Cursor rule Cursor
Use Context Engine CLI (ctx-cli) to search code & the knowledge graph, investigate services, triage/resolve CVE & SAST findings, and apply coding guidelines.
not rated 9 2mo ago A 231 tokens
codegraph
51Cursor rule Cursor
CodeGraph MCP usage guide — when to use which tool.
not rated 9 4mo ago A 819 tokens
copy · 100% MIT
plumber
52Cursor rule Cursor
Plumber, root cause first. Always fix the pipe, not the floor.
not rated 8 3mo ago A 405 tokens
original MIT
rig
53Cursor rule Cursor
Rig MCP usage guide — when to use which tool.
not rated 8 4mo ago A 983 tokens
original Apache-2.0
Cursor rule Cursor needs its repo
Use this rule to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. Triggers on: "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace request flow"…
not rated 8 3mo ago A 0 tokens
original MIT
Cursor rule Cursor
Saropa Lints project guidelines for AI agents.
not rated 8
changed 1mo ago A 512 tokens
original MIT
Cursor rule Cursor
Logging in this project should be detailed, scoped, and extensive. Logs are the primary way to debug test runs, so they should make execution history obvious.
not rated 8 1y ago A 253 tokens
original MIT
cctools
57Cursor rule Cursor
Your task is to help users to write ast-grep rules to search code. User will query you by natural language, and you will write ast-grep rules to search code.
not rated 8 1y ago A 0 tokens
safelint
58Cursor rule Cursor
Run safelint static analysis on the user's project and present Holzmann Power-of-Ten safety violations grouped by file. Use when the user asks for "safelint check", "lint with safelint", "safety review", "Power-of-Ten review", or similar requests for safelint's specific rule set. For generic linting use the project's…
not rated 7 2d ago B 85 tokens
original MIT
Cursor rule Cursor
A development check that reads a stored snapshot of uncaught errors from a web, Electron, or React Native Web interface. It reports whether the development interface has a visible error screen or captured stack trace.
not rated 7 3mo ago A 394 tokens
original MIT
python
60Cursor rule Cursor
You are a Python programming assistant. You will be given a function implementation and a series of unit test results. Your goal is to write a few sentences to explain why your implementation is wrong, as indicated by the tests. You will need this as guidance when you try again later. Only provide the few sentence…
not rated 5 12mo ago A 283 tokens
original MIT
ultracite
61ohansFavour/react-best-practices-agent
Cursor rule Cursor
Ultracite Rules - AI-Ready Formatter and Linter.
not rated 5 4mo ago A 3,481 tokens
Cursor rule Cursor
Verify rendered CSS/layout truth with Visionaire MCP after every visual edit; never claim a visual fix works without a PASS verdict.
not rated 5
changed 15d ago A 529 tokens
original Apache-2.0
synapse
63Cursor rule Cursor
Rules for using Synapse MCP — prefer the graph over grep.
not rated 5 17d ago A 323 tokens
original MIT
debug
64Cursor rule Cursor
Systematic root-cause debugging. Use whenever something is broken, failing, flaky, slow, crashing, or behaving unexpectedly — bug reports, stack traces, failing or flaky tests, regressions, hangs, memory leaks, wrong output, CI-only failures, "works on my machine".
not rated 4 1mo ago A 57 tokens
original MIT
diagnose
65Cursor rule Cursor
name: Issue Re-Diagnosis and Fix Template description: Template for AI to re-diagnose and fix issues that weren't resolved previously. globs.
not rated 4 1y ago A 0 tokens
lintent
66Cursor rule Cursor
Guidelines for fixing lint violations using semantic context from lintent.
not rated 4 8mo ago A 466 tokens
original MIT
cursor-rule
67rn-devtools-hub/rn-devtools-hub
Cursor rule Cursor
Drive the running React Native app through the rn-devtools-hub MCP server. Use when checking whether a change works in the app, tapping or typing in the UI, finding which file renders an element, proving a request succeeded, diagnosing behaviour that looks impossible, or investigating a bug after the fact.
not rated 4
changed 1mo ago A 60 tokens
original MIT
Cursor rule Cursor
Conventions for working with Antimetal investigation data and MCP tools.
not rated 4 4mo ago A 590 tokens
original MIT
codegraph
69codegraph-ai/codegraph-rules-for-agents
Cursor rule Cursor
Code intelligence via local code graph. Always try codegraph tools before grep for structural questions (callers, impact, deps, search).
not rated 3 4mo ago A 617 tokens
original Apache-2.0
nen-conjurer
70Cursor rule Cursor
Failure-mode-driven reliability engineering — enumerate how it breaks, give every mode a verdict, prove every handler with a reproducing test. Use when the user says "flaky", "harden this before launch", "what if this fails", "error handling", "timeout", "retry", "idempotency", or "race condition"; when an incident or…
not rated 3 2mo ago A 126 tokens
original MIT
Cursor rule Cursor
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
not rated 3 2d ago A 41 tokens
original Apache-2.0
Cursor rule Cursor
A set of Cursor editor rules for investigating bugs step by step. Cursor is a code editor with AI-assisted development features.
not rated 3 10mo ago A 2,979 tokens
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: