agentleFS
Sign inStart free
ArangoGutierrezArangoGutierrez/claude-toolkit/.cursor/rules/core.mdc

claude-toolkit / rules

Cursor rule4 starsChanged 3 months agoMITView on GitHub

Core workflow, commit standards, TDD invariant, date/year rules

We split this core.mdc into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Always sign: git commit -s -S (DCO + GPG) — no exceptions

    line 11
  2. Very specific:

    Never use --no-verify — hooks are safety rails

    line 12
  3. Distinctive:

    Never force-push to main/master

    line 13
  4. Distinctive:

    Ask before dispatching to a different model

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
core.mdc
---
description: Core workflow, commit standards, TDD invariant, date/year rules
alwaysApply: true
---
# Core

## Workflow
Phases: brainstorm → plan → code → verify → PR → review → address → CI → merge

## Commits
- Always sign: `git commit -s -S` (DCO + GPG) — no exceptions
- Never use `--no-verify` — hooks are safety rails
- Never force-push to main/master

## TDD Invariant
- RED before GREEN — never write implementation without a failing test
- One phase per turn — never mix test and implementation edits
- Tests are contracts — never weaken tests to pass implementation

## Verification
- Evidence before claim — run tests/lints/scans before asserting success
- File:line references must exist — verify before citing

## Dates & Years
- Source of truth: "Today's date" from system context — never training data
- New files: always current year (2026) — never copy from existing files
- Year ranges: first-year–current (e.g. 2024–2026) only when history applies
- Applies to: copyright headers, changelogs, commits, docs, test fixtures

## Context Economy
- Reference over paste — use file paths not inline code
- Tables over prose — structured data is cheaper
- Delta-only — show only what changed

## Agent Dispatch
- Inherit model from parent unless task requires different capability
- Ask before dispatching to a different model

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free