Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/stellarshenson/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/stellarshenson/claude-code-plugins/devils-advocate)<a href="https://agentmods.dev/plugins/stellarshenson/claude-code-plugins/devils-advocate"><img src="https://agentmods.dev/badge/plugins/stellarshenson/claude-code-plugins/devils-advocate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/stellarshenson/claude-code-plugins/devils-advocate"><img src="https://agentmods.dev/badge/plugins/stellarshenson/claude-code-plugins/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
devils-advocate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"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 pluggable expert adversaries.",
"version": "1.8.22",
"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"
]
}
What it installs
The manifest is a name and a version. 4 skills, 3 commands, 2 agents travel with it, and installing the plugin installs all of them — 511 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 36f8fcd2cc34
- yesterday Changed 22968a1475a9
- 2d ago Changed 8529180fd8ab
- 11d ago Changed 0d1072adfaa4
- 16d ago Changed 8d59088a6a06
- 18d ago Changed 47874c830431
- 19d ago Changed 23be77390a8a
- 23d ago Changed 7d1310e12784
- 24d ago Changed 3ed9b7bbc8b8
- 25d ago First seen · 25 lines scan A 134721fc543e
devils-advocate is a plugin published in the GitHub repository stellarshenson/claude-code-plugins (4 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
pedantic-coder
Zero-tolerance code pedantry — naming precision, casing law, structural symmetry, import discipline, and the obsessive details that separate clean code from correct code.
ai-infra-auto-driven-skills
Agent-ready playbooks for LLM serving benchmarks, SGLang model Day-0 support, capacity planning, profiling, code review, incidents, PR-history dossiers, and SGLang PR/article explainer videos.
git-pr
Committing, PR creation and review triage, and dependency upgrades.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
coderabbit
CodeRabbit integration for Claude Code - local code review and PR comment management.