Agent Plugins Marketplace
← All plugins

devils-advocate

v1.8.5

Critical document analysis with persona-driven risk scoring, iterative scorecard evaluation, and versioned corrections. Includes adversarial-review - hostile red-team review of code and artefacts via fresh claude -p reviewers with eleven pluggable expert adversaries.

Claude Code6 Skills

By Stellars HensonLicense: MIT4 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
6 skill or MCP entries
Source updated
Sep 17, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install devils-advocate for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install devils-advocate-2@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/stellarshenson/claude-code-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/devils-advocate/.

Plugin files

plugins/devils-advocate/
├── .claude-plugin/plugin.json
├── skills/adversarial-review/SKILL.md
├── skills/evaluate/SKILL.md
├── skills/improve/SKILL.md
├── skills/iterate/SKILL.md
├── skills/run/SKILL.md
└── skills/setup/SKILL.md

Included Skills6

adversarial-reviewskills/adversarial-review/SKILL.md

Hostile, independent review - spawn fresh context-free reviewer subagents that try to BREAK a change. Two modes - diff bug-hunt (no tools, inline diff) and whole-repo audit (tools on - slop, brittle design, hardcodings, config drift, broken SoC). Multi-round - find, fix, re-confirm. Use before a risky commit/merge, a UI or terminal-UI ship, a shell installer, trusting an experiment's verdicts or a green test suite, signing off a spec, or publishing docs. Triggers - "adversarial review", "red-team this", "find bugs in my change", "review before ship", "audit the architecture", "UX review", "TUI review", "shell review", "methodology review", "can this test fail", "review my tests", "readability review", "review my README/docs", "deployment review", "review my spec", "acceptance criteria review", "does the code match the spec", "hunt dead weight", "what can I delete", "de-slop this", "find duplicates", "fake citations or fake passes", "review my agent instructions", "audit my skills", "is my harness portable".

evaluateskills/evaluate/SKILL.md

Generate baseline devil's advocate evaluation. Produces concern catalogue with risk scores and scorecard. Requires setup to have been run first (devils_advocate.md and fact_repository.md must exist).

improveskills/improve/SKILL.md

Bridge between evaluate and iterate. Asks user how to address devil's concerns - user suggestions, auto-apply recommended options, or planning mode. Now integrated into iterate's Step 1 - use /devils-advocate:iterate directly.

iterateskills/iterate/SKILL.md

Improve document based on devil's concerns, create versioned file, re-score, rename with residual. Clear 4-step workflow - improve, version, score, rename. Re-scores in place when user made changes outside Claude.

runskills/run/SKILL.md

Run the full devil's advocate workflow end-to-end. Setup persona, evaluate baseline, then iterate corrections until residual risk is acceptable. Use when the user wants the complete analysis in one go.

setupskills/setup/SKILL.md

Set up devil's advocate persona and fact repository for a target document. Use when starting a new critical analysis. Builds the devil persona (role, biases, triggers) and harvests verified facts from source materials.

Plugin manifests1

plugins/devils-advocate/.claude-plugin/plugin.json
{
  "name": "devils-advocate",
  "description": "Critical document analysis with persona-driven risk scoring, iterative scorecard evaluation, and versioned corrections. Includes adversarial-review - hostile red-team review of code and artefacts via fresh claude -p reviewers with eleven pluggable expert adversaries.",
  "version": "1.8.5",
  "license": "MIT",
  "author": {
    "name": "Stellars Henson",
    "email": "[email protected]"
  },
  "keywords": [
    "critique",
    "analysis",
    "scorecard",
    "risk",
    "devil",
    "advocate",
    "persona",
    "evaluation",
    "adversarial-review",
    "red-team",
    "code-review",
    "audit"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[devils-advocate on Agent Plugins Marketplace](https://pluginsmp.com/plugins/devils-advocate-2)