Cursor rules for Claude Code

118 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

sync-plate-ui

01

udecode/plate

Cursor rule Claude CodeCursor

Sync Plate registry UI into downstream apps with fork-aware comparison, scoped apply and changelog tracking.

not rated 17k +9 changed 3d ago A 19 tokens

use-agent-skills

02

learningmatter-mit/AtomisticSkills

Cursor rule Claude CodeCursor

Discover available AtomisticSkills by scanning skills/ frontmatter. Use this to find skills relevant to a research task.

not rated 179 +4 changed 9d ago A 236 tokens original MIT

code-comments

03

fmflurry/settings-opencode

Cursor rule Claude CodeCursor

Default to no comment. Code, names, and tests carry intent. A comment must justify its existence.

not rated 171 yesterday A 1,501 tokens original MIT

agenticworkflow

04

idoforgod/Dissertation-Simulator-AgenticWorkflow

Cursor rule Claude CodeCursor

A set of project rules for applying the AgenticWorkflow method to every task. It defines a research-to-planning-to-implementation process, shared-state rules, and a required review process before code changes.

not rated 108 4mo ago A 1,803 tokens original MIT

f2s-task

05

double-coding-lab/Flow2Spec

Cursor rule Claude CodeCursor

A rule for tracking code changes in .task files when the project's flow2spec configuration enables tracking for a relevant type of work.

not rated 51 +1 16d ago A 5,259 tokens original MIT

skill-check

06

olgasafonova/SkillCheck-Free

Cursor rule Claude CodeCursor

Validates skills against best practices. Use when user says 'check skill', 'skillcheck', or 'validate SKILL.md'.

not rated 41 changed 6d ago A 26 tokens original MIT

dashboard-home

07

eliornl/rolemule

Cursor rule Claude CodeCursor

Dashboard home page — application list, search/filter/sort, bulk actions, inline status, load-more, session state.

not rated 38 +1 yesterday A 0 tokens original MIT

hatch3r/hatch3r

Cursor rule Claude CodeCursor

Mandatory agent delegation, skill loading, and sub-agent usage directives for ALL tasks in ALL contexts.

not rated 26 20d ago A 10,868 tokens original MIT

reqforge

10

zxpmail/ReqForge

Cursor rule Claude CodeCursor

ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, review. /change-manager for brownfield.

not rated 18 9d ago A 1,753 tokens original MIT

qualidade

11

ReadyToGo-Education/fluxo_criativo

Cursor rule Claude CodeCursor

Regras de qualidade obrigatórias para copy e design — aplicar em todo material gerado.

not rated 17 +1 today A 490 tokens

stackhawk-hawkscan

12

stackhawk/agent-skills

Cursor rule Claude CodeCursor

HawkScan DAST security scanning. Use when the user asks to run or perform a security or DAST scan, to test an app or API for vulnerabilities, or to verify a vulnerability is fixed — and proactively right after you complete a code change (feature, bugfix, refactor); "done" means "done and secure" (configure, scan, fix…

not rated 16 changed 6d ago A 7,301 tokens original MIT

product-agent

13

devjefferson/synapos

Cursor rule Claude CodeCursor

Master Prompt - Assistente de Gestão de Projetos.

not rated 13 18d ago A 10 tokens

coach

14

mreider/agilemarkdown

Cursor rule Claude CodeCursor

Agile Markdown coach mode. AI is the dev pair, the human is the product manager. Hard rules refuse, working agreements nudge.

not rated 8 4mo ago D 2,469 tokens original MIT

skill-writer

15

theneoai/skill-writer

Cursor rule Claude CodeCursor

Cursor rule "skill-writer" from theneoai/skill-writer, covering skill summary, §0 quick start — 5 common workflows, workflow a — "i want to create a new skill", workflow c — "my skill scored below 700 (fail)" and workflow d — "i want to deploy my skill".

not rated 8 5mo ago A 6,332 tokens original MIT

the-loop

16

MadaraUchiha-314/the-loop

Cursor rule Claude CodeCursor

If .the-loop/harness-config.yaml exists in this repository, the-loop is initialized here. Operating rules: plan → execute → self/critic-review → escalate. Read .the-loop/harness-config.yaml (the agent's config — the CLI never reads it) and follow the the-loop skill before working any ticket. If the file does not…

not rated 7 changed 1mo ago A 151 tokens original MIT

ch015

17

ch015/code-pentester

Cursor rule Claude CodeCursor

A source-code security assessment system for vulnerability checks, architecture reviews, penetration testing, red-team analysis, compliance checks, and reports.

not rated 4 2d ago A 38 tokens original MIT

reinforcement

18

erniker/understudy

Cursor rule Claude CodeCursor

Caveman mode — terse-style reinforcement (always applies).

not rated 2 19d ago A 188 tokens original MIT

shipjaw.cursor-rule

19

XyDisorder/shipjaw

Cursor rule Claude CodeCursor

Shipjaw continuation contract for this repo — docs-first, INDEX-led, gate before done.

not rated 2 9d ago A 567 tokens original MIT

inference-context

20

belt-sh/skills

Cursor rule Claude CodeCursor

How to use belt skills, knowledge, and apps surfaced by hooks.

not rated 2 19d ago A 249 tokens original MIT

pathology-ml

21

lamia482/claude-in-cursor

Cursor rule Claude CodeCursor

Practice on Pathology by using Computer Vision and Image Processing and Deep Learning and Machine Learning.

not rated 2 4mo ago A 1,096 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: