agentleFS
thebiglaskowskithebiglaskowski/claude-sentient/.cursor/rules/claude-sentient.mdc

claude-sentient / rules

Cursor rule2 starsChanged 7 months agoMITView on GitHub

Claude Sentient conventions for Cursor IDE

  • Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.

    Of the Cursor rule files we read, the 4,329 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository6 other files it gives its agents.

The file

We split this claude-sentient.mdc into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    No magic numbers — use named constants

    line 15
  2. Very specific:

    No debug/console.log left in committed code

    line 17
  3. Distinctive:

    Always propagate errors explicitly (never swallow with empty catch)

    line 20
  4. Distinctive:

    Write tests for new functionality before considering work done

    line 25
  5. Distinctive:

    Test files mirror source structure

    line 27
  6. Distinctive:

    Never commit with failing tests

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 6,873 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
claude-sentient.mdc
---
description: Claude Sentient conventions for Cursor IDE
globs: ["**/*"]
alwaysApply: true
---

# Claude Sentient — Cursor Rules

This project uses Claude Sentient, an autonomous development orchestration layer.

## Core Conventions

### Code Quality
- Function max 50 lines, cyclomatic complexity ≤ 10, nesting depth ≤ 3
- No magic numbers — use named constants
- Early returns over nested conditionals
- No debug/console.log left in committed code

### Error Handling
- Always propagate errors explicitly (never swallow with empty catch)
- Wrap errors with context: "doing X: {err}"
- Map errors to appropriate output types at boundaries

### Testing
- Write tests for new functionality before considering work done
- Table-driven / parameterized tests for multiple cases
- Test files mirror source structure

### Git
- Conventional commits: `feat:`, `fix:`, `chore:`, `docs:`, `refactor:`
- Quality gates before commit: lint → test → build
- Never commit with failing tests

## Project Structure

```
.claude/commands/    # /cs-* slash commands
.claude/hooks/       # Session lifecycle hooks (.cjs)
.claude/rules/       # Always-loaded and path-scoped rules
agents/              # Agent role definitions (YAML + MD)
profiles/            # Language profiles (YAML)
schemas/             # JSON schemas for validation
examples/            # Project CLAUDE.md templates
```

## Running Quality Gates

```bash
# Shell profile (default for this project)
shellcheck install.sh uninstall.sh generate-checksums.sh

# All tests
node profiles/__tests__/test-profiles.js
node .claude/hooks/__tests__/test-hooks.js
node .claude/commands/__tests__/test-commands.js
node agents/__tests__/test-agents.js
node schemas/__tests__/test-schemas.js
node integration/__tests__/test-integration.js
```

## Key Files

- `CLAUDE.md` — Project overview and commands reference
- `CHANGELOG.md` — Version history
- `STATUS.md` — Current development state
- `DECISIONS.md` — Architecture decision records
- `.claude/rules/learnings.md` — Captured decisions and learnings

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.