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:

$ npx skills add getsentry/warden

$ pnpx skills add getsentry/warden

$ bunx skills add getsentry/warden

Claude Code Marketplace

Install directly from the Claude Code marketplace:

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

The /warden skill will be available immediately.

What It Does

The /warden skill teaches agents how to:

Run Warden against uncommitted changes before committing
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 commit".

Usage

In any agent that supports the spec (like Claude Code), use /warden before committing:

> Use /warden before committing

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

How It Works

The skill follows a progressive disclosure pattern. The main SKILL.md contains the core workflow. Reference files load on demand when the agent needs deeper detail:

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

This keeps agent context small for common tasks while making the full reference available when needed.

Discovery

Agents discover the skill by scanning for SKILL.md files in known directories. The skill's 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

No registration or configuration required. If the directory exists, agents that support the agentskills.io spec will find it.

Pre-Commit Workflow

The primary use case the skill optimizes for:

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, not a loop. The skill instructs agents to run Warden once, fix what it finds, and move on.