Agent skills for the fallow codebase intelligence layer for TypeScript and JavaScript.
Agent skills for [fallow](https://github.com/fallow-rs/fallow), codebase intelligence for TypeScript and JavaScript. The static layer reports quality, changed-code risk, cleanup opportunities, circular dependencies, code duplication, complexity hotspots, architecture boundary violations, and design-system styling drift in milliseconds. Optional runtime intelligence adds production execution evidence so agents can delete cold code, flag hot-path changes, and retire stale flags with proof. 123 framework plugins, zero configuration. Works with any agent that supports the [Agent Skills](https://agentskills.io) specification: Claude Code, Cursor, OpenAI Codex, Windsurf, GitHub Copilot, Gemini CLI, Amp, and [30+ more](https://agentskills.io).
> **Linters enforce style. Formatters enforce consistency. Fallow enforces relevance.** Linters work file by file. TypeScript works type by type. Neither builds the full module graph, so neither can see what nothing depends on. Fallow does, in milliseconds. These skills teach agents *how* to use fallow effectively: which commands to run, what flags to use, how to interpret output, and how to avoid common pitfalls.
## Quick Start
### Agent Skills CLI
```bash
npx skills add fallow-rs/fallow-skills
```
### Claude Code
```bash
/install fallow-rs/fallow-skills
```
### Agent-specific CLI shortcuts
```bash
npx skills add fallow-rs/fallow-skills --agent windsurf
npx skills add fallow-rs/fallow-skills --agent amp
gemini skills install https://github.com/fallow-rs/fallow-skills.git
```
### Manual install
```bash
tmp=$(mktemp -d)
git clone https://github.com/fallow-rs/fallow-skills.git "$tmp/fallow-skills"
```
Copy the `fallow` skill directory into your agent's skills folder:
```bash
# OpenAI Codex, Amp, and agents using the shared Agent Skills location
mkdir -p ~/.agents/skills
cp -R "$tmp/fallow-skills/fallow/skills/fallow" ~/.agents/skills/fallow
# Claude Code
mkdir -p ~/.claude/skills
cp -R "$tmp/fallow-skills/fallow/skills/fallow" ~/.claude/skills/fallow
# Cursor
mkdir -p ~/.cursor/skills
cp -R "$tmp/fallow-skills/fallow/skills/fallow" ~/.cursor/skills/fallow
# Windsurf
mkdir -p ~/.codeium/windsurf/skills
cp -R "$tmp/fallow-skills/fallow/skills/fallow" ~/.codeium/windsurf/skills/fallow
# GitHub Copilot
mkdir -p .github/skills
cp -R "$tmp/fallow-skills/fallow/skills/fallow" .github/skills/fallow
```
Other agents
Use `npx skills add fallow-rs/fallow-skills --all` for installer-managed discovery, or copy `fallow/skills/fallow` into your agent's skills location as `fallow`. This skill follows the open [Agent Skills](https://agentskills.io) specification and works with any compatible agent.
## Prerequisites
Fallow must be installed in the target project:
```bash
npm install -g fallow # prebuilt binaries
npx fallow # or run without installing
```
See the [installation guide](https://docs.fallow.tools/installation) for all options including `cargo install fallow-cli`.
## Available Skills
| Skill | Description | Trigger phrases |
|---|---|---|
| [fallow](https://github.com/fallow-rs/fallow-skills/tree/HEAD/fallow/) | Codebase intelligence for JS and TS, code and styles: quality, changed-code risk, cleanup opportunities, circular deps, duplication, complexity, design-system drift, and runtime evidence | "check code health", "audit this PR", "find cleanup opportunities", "find duplicates", "what code actually runs" |
## What's Included
### fallow
| Category | What it does |
|---|---|
| **Cleanup** | Find unused files, exports, types, dependencies, enum/class members, stale suppressions, and other safe cleanup candidates |
| **Duplication** | Find code clones with 4 modes: strict, mild, weak, semantic |
| **Complexity** | Function complexity analysis, hotspot detection, health scores |
| **Auto-Fix** | Remove unused exports and dependencies with dry-run preview |
| **CI** | GitHub Actions, SARIF upload, baseline comparison, PR-scoped checks |
| **Monorepo** | Per-workspace analysis with cross-package resolution |
| **Debug** | Trace export usage chains, file edges, and dependency usage |
### Reference Documentation
- **[CLI Reference](https://github.com/fallow-rs/fallow-skills/blob/HEAD/fallow/references/cli-reference.md)**: all 10 commands, flags, JSON output structure, config format
- **[Gotchas](https://github.com/fallow-rs/fallow-skills/blob/HEAD/fallow/references/gotchas.md)**: 19 pitfalls with WRONG/CORRECT examples
- **[Patterns](https://github.com/fallow-rs/fallow-skills/blob/HEAD/fallow/references/patterns.md)**: 14 workflow recipes for CI, monorepos, migration, incremental adoption
## Example Prompts
Once installed, you can use natural language:
- "Audit the codebase quality"
- "Are there any unused dependencies?"
- "Find code duplication in the codebase"
- "Clean up unused exports"
- "Set up a CI quality gate"
- "Check the complexity of this codebase"
- "Why is this export flagged as unused?"
- "Check if this PR introduces quality risk"
- "Find unused files in the payments package"
- "What's the duplication percentage?"
## How It Works
```
User: "Find all unused exports"
↓
Agent loads fallow skill
↓
Skill instructs: run `fallow dead-code --format json --quiet --unused-exports`
↓
Agent executes command, parses JSON output
↓
Agent summarizes findings with file paths and line numbers
```
The skill provides agents with:
1. **Command knowledge**: which fallow command + flags to use for each task
2. **Output parsing**: how to interpret JSON results
3. **Guardrails**: always dry-run before fix, never run watch, use `--yes` in non-TTY
4. **Debugging**: how to trace false positives with `--trace`
## Contributing
See [CLAUDE.md](https://github.com/fallow-rs/fallow-skills/blob/HEAD/CLAUDE.md) for repository structure, skill creation guidelines, and quality standards.
## Related
- [fallow](https://github.com/fallow-rs/fallow): codebase intelligence for TypeScript and JavaScript, a single pass over code and styles
- [fallow-docs](https://docs.fallow.tools): Official documentation
- [VS Code extension](https://marketplace.visualstudio.com/items?itemName=fallow-rs.fallow-vscode): Real-time diagnostics in your editor
- [Agent Skills specification](https://agentskills.io): The open standard this skill follows
## License
MIT. See [LICENSE](https://github.com/fallow-rs/fallow-skills/tree/HEAD/LICENSE) for details.
