Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.fallow.tools/llms.txt

Use this file to discover all available pages before exploring further.

Agent skills give AI coding agents structured knowledge about how to use fallow. Skills cover when to run each command, what flags to use, how to read the output, and how to avoid common pitfalls. Instead of relying on the agent’s general knowledge, skills provide precise, up-to-date instructions for dead code analysis, circular dependency detection, duplication, and complexity hotspots.
Skills work alongside the CLI and MCP integrations. They tell agents how to use fallow effectively, while the CLI and MCP provide the tools to do it.

​
What’s included

The fallow-skills package includes:
ComponentDescription
Analysis skillWorkflows for unused code, duplication, complexity, boundary analysis, auto-fix, and CI setup
CLI referenceComplete command specs, flags, output formats, and configuration
GotchasCommon pitfalls with correct vs. incorrect examples (e.g., fix --yes in non-TTY)
Workflow patternsRecipes for CI pipelines, monorepo analysis, migrating from knip/jscpd, and incremental adoption

​
Installation

/plugin marketplace add fallow-rs/fallow-skills
/plugin install fallow-skills@fallow-rs/fallow-skills
Skills follow the open Agent Skills specification and work with any compatible agent.

​
What agents can do after installation

Once installed, agents know how to respond to natural language requests like these:

Find dead code

“Find all unused exports in this project”. Agent runs fallow dead-code --format json --quiet --unused-exports and summarizes findings.

Clean up dependencies

“Are there any unused dependencies?” Agent runs targeted analysis and suggests removals.

Detect duplication

“Find code duplication in the codebase”. Agent runs fallow dupes with the right mode and interprets clone families.

Auto-fix

“Remove unused exports”. Agent runs dry-run first, shows proposed changes, then applies with --yes.

CI setup

“Set up a dead code check in CI”. Agent generates the correct GitHub Actions workflow with baselines.

Debug false positives

“Why is this export flagged?” Agent uses --trace to investigate and suggests suppression if needed.

​
Workflow recipe: adopt Fallow in an existing repo

When the goal is to bring an existing codebase to a clean Fallow policy (not just audit a single PR), fallow’s approach is to hand the cleanup work to the agent: fallow finds the problems, the agent fixes them in code. Three ways to run this, pick whichever your agent supports:
  1. Install the skill (best). fallow-skills ships the full adoption workflow. Once installed, the agent does not need to fetch docs URLs during use. Installation is one line per agent, above.
  2. Add the MCP server. Combine with the skill or use standalone. The agent gets audit, dead_code, dupes, and health as structured tools with _meta explanations on every finding. See MCP.
  3. Paste the prompt below. Self-contained fallback for agents without skill or MCP support, or for sandboxed agents that cannot fetch URLs.
Adopt Fallow in this repository.

Goal:
- use full-repo analysis first (`fallow`, `fallow dead-code`, `fallow dupes`, `fallow health`), not `fallow audit`
- fix real dead code, duplication, and complexity issues in code
- model intentional exceptions with the narrowest correct mechanism
- end with no functions above the repo's chosen health thresholds, or a consciously widened threshold with written justification
- then set up `fallow audit` as a PR gate

Process:
1. Run `npx fallow`, then `npx fallow dead-code`, `npx fallow dupes`, and `npx fallow health`. Use `--format json` for structured output.
2. If no config exists, run `fallow init` and create a minimal repo policy.
3. Fix high-confidence issues first:
   - unresolved imports
   - unlisted dependencies
   - unused files (sanity-check with `fallow list --entry-points`)
   - unused dependencies
4. For each remaining finding, choose one path:
   - fix it in code (preferred)
   - model it in config
   - add a narrow inline exception only if it is truly one-off
5. Match reasons to mechanisms:
   - external API: `@public` / `@internal` / `@beta` / `@alpha` JSDoc tags, or `publicPackages`
   - runtime or framework entry point: `entry`, `dynamicallyLoaded`, plugin-aware config
   - generated code: `ignorePatterns`, `health.ignore`
   - intentionally retained dependency: `ignoreDependencies`
   - intentional unused export: `@expected-unused` (preferred over inline comments because it self-cleans)
   - one-off false positive: `fallow-ignore-next-line`
   - repo-wide policy: `rules`, `health`, duplication settings, `overrides`
6. Prefer config-level modeling over repeated suppression.
7. Keep every exception narrow and explain why it exists in a commit message.
8. Re-run Fallow after each batch until the repo is clean under the chosen policy.
9. Only after repo cleanup, run `npx fallow audit` and wire it into CI.

At the end, report:
- code changes
- config changes
- exceptions added and why
- anything left
- the final commands and outputs that show the repo is clean

​
Skills vs MCP vs CLI

SkillsMCPCLI
What it providesKnowledge about how to use fallowStructured tool interfaceDirect command execution
SetupOne-time install per agentMCP server configurationfallow binary in PATH
Agent supportAny agent with skill supportAgents with MCP supportAny agent that runs shell commands
Best forTeaching agents fallow best practicesTyped tool calling in agent frameworksUniversal compatibility
For the best experience, combine all three. Install the skill for knowledge, configure MCP for structured tool calling, and keep fallow in PATH for CLI fallback.

​
See also

Agent integration

CLI and MCP integration for AI agents.

CI integration

Catch codebase issues in your CI pipeline.

VS Code extension

Real-time feedback for human developers.