Index of every page on this site: llms.txt
All skills
getsentry avatar

/warden

@2998ac7
by Sentrygetsentry/mobilebuildmcp6.6k stars
329
Run it yourself

Run Warden to analyze code changes before committing. Use when asked to "run warden", "check my changes", "review before commit", "warden config", "warden.toml", "create a warden skill", "add trigger", or any Warden-related local development task.

Use this Skill: https://skilld.dev/gh/getsentry/mobilebuildmcp/warden

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencescli-reference.md

≈1.1k tokens on demand. Your agent reads this file only when SKILL.md points to it.

CLI Reference

Usage

warden [command] [targets...] [options]

Analyze code for security issues and code quality.

Commands

Command Description
(default) Run analysis on targets or using warden.toml skills
init Initialize warden.toml and GitHub workflow
add [skill] Add a skill to warden.toml
sync [remote] Update cached remote skills to latest
setup-app Create a GitHub App for Warden via manifest flow

Targets

Target Description
<files> Analyze specific files (e.g., src/auth.ts)
<glob> Analyze files matching pattern (e.g., "src/**/*.ts")
<git-ref> Analyze changes from git ref (e.g., HEAD~3, main..feature)
(none) Analyze uncommitted changes using warden.toml skills

Ambiguous targets (no path separator, no extension) are resolved by checking if a file exists at the path. Use --git to force git ref interpretation.

Options

Option Description
--skill <name> Run only this skill (default: run all built-in skills)
--config <path> Path to warden.toml (default: ./warden.toml)
-m, --model <model> Model to use (fallback when not set in config)
--json Output results as JSON
-o, --output <path> Write full run output to a JSONL file
--fail-on <severity> Exit with code 1 if findings >= severity
--report-on <severity> Only show findings >= severity in output
--fix Automatically apply all suggested fixes
--parallel <n> Max concurrent skill executions (default: 4)
--git Force ambiguous targets to be treated as git refs
--offline Use cached remote skills without network access
-q, --quiet Errors and final summary only
-v, --verbose Show real-time findings and hunk details
-vv Show debug info (token counts, latencies)
--debug Enable debug output (equivalent to -vv)
--log Use log output (no animations, timestamped)
--color / --no-color Override color detection
-h, --help Show help message
-V, --version Show version number

Per-Command Options

Init:

Option Description
-f, --force Overwrite existing files

Add:

Option Description
--list List available skills
--remote <ref> Remote repository (owner/repo, URL, or with @sha)
--force Bypass skill cache and fetch latest

Sync:

Option Description
--remote <ref> Specific remote to sync (default: all)

Setup-app:

Option Description
--org <name> Create under organization (default: personal)
--port <number> Local server port (default: 3000)
--timeout <sec> Callback timeout in seconds (default: 300)
--name <string> Custom app name (default: Warden)
--no-open Print URL instead of opening browser

Severity Levels

Used in --fail-on and --report-on:

Level Meaning
high Must fix before merge
medium Worth reviewing
low Minor improvement
off Disable the threshold

Exit Codes

Code Meaning
0 No findings at or above --fail-on threshold
1 Findings at or above --fail-on threshold

Examples

# Initialize
warden init

# Interactive skill selection
warden add
warden add <skill-name>
warden add --list

# Remote skills
warden add --remote <org>/<repo> --skill <skill-name>
warden add --remote https://github.com/<org>/<repo> --skill <skill-name>
warden add --remote <org>/<repo>@<ref> --skill <skill-name>

# Run analysis
warden                                  # Skills from warden.toml
warden src/auth.ts                      # Specific file
warden src/auth.ts --skill <skill-name>
warden "src/**/*.ts"                    # Glob pattern
warden HEAD~3                           # Git changes
warden HEAD~3 --skill <skill-name>
warden main..HEAD                       # Branch diff

# Output control
warden --json
warden --fail-on high
warden -o results.jsonl

# Fix mode
warden --fix

# Cached skills only
warden --offline
warden sync                             # Update all unpinned remote skills

# GitHub App setup
warden setup-app
warden setup-app --org myorg

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill provides a code analysis tool that can fetch extension 'skills' from external GitHub repositories and analyzes code changes in pull requests, creating a surface for indirect prompt injection from malicious project files.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 2998ac7. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 7 months ago

README badge

README badge for getsentry/mobilebuildmcp/warden