agentleFS
hiromailyhiromaily/go-crypto-wallet/.cursor/rules/agent-files.mdc

go-crypto-wallet / rules

Cursor rule128 starsChanged 6 months agoMITView on GitHub

Agent Files

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create new commands in .claude/commands/

    line 65
  2. Very specific:

    Only place README.md in .cursor/commands/

    line 66
  3. Very specific:

    Place SKILL.md in .claude/skills/ or .cursor/skills/.

    line 127
  4. Very specific:

    When editing .claude/ or .cursor/:

    line 135

≈ “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
agent-files.mdc
---
description: Agent Files
globs: 
  - ".claude/**"
  - ".cursor/**"
  - ".codex/**"
  - ".github/copilot-instructions.md"
alwaysApply: false
---


# Agent Files

This rule applies when editing `.claude/`, `.cursor/`, `.codex/`, or `.github/copilot-instructions.md`.

## Single Source of Truth (SSOT) Design

AI Agent configuration files are managed with **Claude Code's `.claude/` directory as the single source**. Other agent configurations are auto-generated or symlinked.

```
.claude/                    ← SSOT (Source of Truth)
├── commands/               ← Slash commands
├── rules/                  ← Rules (*.md)
└── skills/                 ← Skills (SKILL.md)

.cursor/                    ← Auto-generated / Symlinked
├── commands/README.md      ← Reference only (uses .claude/commands)
├── rules/*.mdc             ← Auto-generated (make sync-cursor-rules)
└── skills/                 ← Symlink → ../.claude/skills

.codex/                     ← TODO (Future support)
.github/copilot-instructions.md ← TODO (Future support)
```

## Supported AI Agents

| Agent | Version | Status | Config Location |
|-------|---------|--------|-----------------|
| Claude Code | v2 | ✅ Active | `.claude/` (SSOT) |
| Cursor | v2 | ✅ Active | `.cursor/` (Auto-generated) |
| Codex | v0.80 | 📋 TODO | `.codex/` |
| GitHub Copilot | 2026 | 📋 TODO | `.github/copilot-instructions.md` |

## File Reference Format

### Claude Code

```markdown
- Follow @AGENTS.md for guidelines
- Refer to @docs/guidelines/coding-conventions.md
```

### Cursor

Supports the same `@path` format. No conversion needed.

## Directory-Specific Rules

### `.claude/commands/`

Location for slash command definitions. Automatically loaded by Cursor as well.

**Editing Notes:**

- Create new commands in `.claude/commands/`
- Only place README.md in `.cursor/commands/`

### `.claude/rules/`

Rule files for Claude Code (`.md`).

**Format:**

```markdown
---
paths:
  - "**/*.go"
  - "**/*.ts"
---

# Rule Title

Rule content...
```

- Without `paths:` → Applies to all instructions (global rule)
- With `paths:` → Applies when editing files matching the specified patterns

### `.claude/skills/`

Location for Skills (MCP) definitions. Each skill has `SKILL.md` in its subdirectory.

```
.claude/skills/
├── go-development/SKILL.md
├── git-workflow/SKILL.md
└── db-migration/SKILL.md
```

### `.cursor/rules/`

**Auto-generated files - DO NOT EDIT DIRECTLY**

Auto-generated from Claude rules. Conversion rules:

| Claude | Cursor |
|--------|--------|
| No `paths:` | `alwaysApply: true` |
| Has `paths:` | `globs:` + `alwaysApply: false` |
| First `# Heading` | `description:` |
| `.md` | `.mdc` |

**Sync Command:**

```bash
make sync-cursor-rules
```

> **IMPORTANT**: After modifying any files in `.claude/rules/`, you MUST run `make sync-cursor-rules` to synchronize with `.cursor/rules/`. This ensures both Claude Code and Cursor use the same rules.

## Model Context Protocol (MCP) / Skills

MCP, proposed since late 2024, is now widespread as of 2026. AI Agents can use repository scripts and local servers as "Skills".

### Claude Code / Cursor

Place `SKILL.md` in `.claude/skills/` or `.cursor/skills/`.

### Codex (Future Support)

For CLI-based Codex agent, Shell/Python scripts are expected to be bound as Skills and invoked like `@database_tool`.

## Editing Checklist

When editing `.claude/` or `.cursor/`:

- [ ] Make changes to `.claude/` (SSOT)
- [ ] Do NOT edit `.cursor/rules/` directly
- [ ] **Run `make sync-cursor-rules` after modifying `.claude/rules/`** (Required)
- [ ] Check if README.md needs updating

## Related Documents

- @.cursor/rules/README.md - Cursor rules specification
- @.cursor/commands/README.md - Commands description
- @AGENTS.md - Project-wide guidelines

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.

Reviews can't be read right now.

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.