Agent Skill

Warden ships with an agentskills.io skill that lets AI coding agents run Warden on your behalf.

Install

Use the skills installer for Claude Code, OpenCode, Codex, or Cursor:

pnpx skills add getsentry/warden

For Claude Code marketplace installs:

claude plugin marketplace add getsentry/warden
claude plugin install warden@warden

The /warden skill is available immediately.

What It Does

The /warden skill teaches agents how to:

Run Warden against current branch changes before review.
Interpret findings and fix the code.
Configure skills in warden.toml.
Create custom skills.

Agents load it automatically when they detect trigger phrases like “run warden”, “check my changes”, or “review before PR”.

Usage

Ask an agent that supports the spec to use Warden before opening a pull request:

> Use /warden before opening a PR

The agent runs warden, reads the output, and fixes what it finds.

How It Works

The skill follows progressive disclosure. SKILL.md contains the core workflow, and reference files load when the agent needs deeper detail.

File	Loaded when
`SKILL.md`	Always, for the core workflow.
`references/cli-reference.md`	Full option details and per-command flags.
`references/configuration.md`	Editing `warden.toml`, triggers, and troubleshooting.
`references/config-schema.md`	Exact field names, types, and defaults.
`references/creating-skills.md`	Writing custom and remote skills.

Discovery

Agents discover the skill by scanning known directories for SKILL.md files. The name field in frontmatter must match its directory name:

.claude/skills/warden/
├── SKILL.md
└── references/
    ├── cli-reference.md
    ├── configuration.md
    ├── config-schema.md
    └── creating-skills.md

Pre-Commit Workflow

The primary workflow:

You make code changes, or an agent makes them for you.
Before committing, the agent runs warden.
The agent reads findings and fixes issues.
The agent commits the clean code.

One pass. The skill instructs agents to run Warden once, fix what it finds, and move on.