cursorrules

A Git-based knowledge system that stores agent guidance and lessons in ordinary Markdown files. It selects topic-specific instructions, such as Python, TypeScript, React, or test-driven development (writing tests before implementation).

In plain words
What is it for?
Loading relevant coding rules before changes, and recording new lessons or corrections after mistakes.
Why use it?
It helps the agent reuse project conventions and avoid repeating mistakes across coding sessions.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/sordi-ai/skill-everything/cursorrules
Clone the repo
git clone --depth 1 https://github.com/sordi-ai/skill-everything

Made for: Cursor.

Per session 1,069 This file is loaded in full into every session.
When invoked 1,069 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01069 $0.01069
Opus 5 $0.00535 $0.00535
Sonnet 5 $0.00214 $0.00214
Haiku 4.5 $0.00107 $0.00107

Measured 2d ago against content hash c0f7074f9ecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursorrules · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-everything

You are using the skill-everything knowledge system: agent memory in plain Markdown, versioned in Git, that grows by capturing your own past mistakes as committed rules.

Your responsibilities

  1. Before every implementation: check the sub-skill directory below, load the matching skill via @file:./skills/<name>/SKILL.md references.
  2. After every mistake: execute the self-extension workflow.
  3. When you learn something new: add it to the appropriate category.

Sub-skill directory

Trigger Sub-skill Load via
writing code, refactoring, review Code Quality @file:./skills/code-quality/SKILL.md
python code, type hints, python packaging Python @file:./skills/python/SKILL.md
fastapi endpoint, pydantic model, async api FastAPI @file:./skills/fastapi/SKILL.md
langchain, lcel chain, agent framework LangChain / Agent Framework Conventions @file:./skills/langchain/SKILL.md
typescript code, strict types, async typescript TypeScript @file:./skills/typescript/SKILL.md
react component, react hooks, react performance React @file:./skills/react/SKILL.md
test-driven development, red green refactor, test first Test-Driven Development @file:./skills/tdd/SKILL.md
debugging, troubleshooting, root cause analysis, isolating bugs Debugging @file:./skills/debugging/SKILL.md
security review, vulnerability check, auth implementation Security Review Depth @file:./skills/security-review/SKILL.md
git commit, branch, pull request Git Conventions @file:./skills/git-conventions/SKILL.md
gh cli, github pr create, github issues GitHub CLI (gh) Conventions @file:./skills/github-cli/SKILL.md
finish branch, pre-merge checklist, branch cleanup Closing Out a Feature Branch @file:./skills/branch-finishing/SKILL.md
creating PR, deployment, review checklist Review & Deployment @file:./skills/review-deployment/SKILL.md
dockerfile, docker compose, container build Docker / Container Conventions @file:./skills/docker/SKILL.md
bash script, shell script, posix scripting Bash / POSIX Scripting @file:./skills/shell-scripting/SKILL.md
database schema, migration, table design Database Schema Design @file:./skills/db-schema/SKILL.md
svg edit, svg review, diagram, pixel review SVG Check @file:./skills/svg-check/SKILL.md
architecture diagram, mermaid diagram, drawio file Diagrams (draw.io / Mermaid) @file:./skills/drawio/SKILL.md
project-specific knowledge, business rules Domain Knowledge (template) @file:./skills/domain-template/SKILL.md
made or corrected a mistake, learn from this Error Log @file:./skills/error-log/SKILL.md
brainstorming, idea generation, divergent thinking Brainstorming @file:./skills/brainstorming/SKILL.md
implementation plan, planning before code, scope definition Implementation Plan @file:./skills/implementation-plan/SKILL.md
executing self-extension Self-Extension Workflow @file:./skills/self-extension-workflow/SKILL.md

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 65 lines · 1,069 tokens per session scan A c0f7074f9ecb

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository sordi-ai/skill-everything (19 stars, last pushed 3mo ago), licensed MIT. It adds 1,069 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.