devils-advocate

devils-advocate is a skill for Claude Code from damionrashford/Adversaria. It costs 72 tokens per session (1,955 once invoked), scanned A, original, MIT.

An adversarial review process for testing an idea, proposal, or argument. It builds the strongest version of the case, challenges it from several reasoning traditions, and gives a final judgment.

In plain words
What is it for?
Asking for a devil's-advocate review, a full challenge, or a detailed teardown of an argument.
Why use it?
It helps expose weak assumptions and overlooked objections before you act on an idea or present it to others.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the adversaria plugin — 5 skills, 3 agents, 4 hooks shipped together

Good fit Asking for a devil's-advocate review, a full challenge, or a detailed teardown of an argument.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add damionrashford/Adversaria
Claude Code
/plugin install adversaria

Made for: Claude Code.

Or install adversaria, the plugin that ships this one along with the rest of its 5 skills, 3 agents, 4 hooks.

Wrote 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.

agentmods badge for devils-advocate

README.md
[![agentmods](https://agentmods.dev/badge/skills/damionrashford/adversaria/devils-advocate/github.svg)](https://agentmods.dev/skills/damionrashford/adversaria/devils-advocate)
Your own site
<a href="https://agentmods.dev/skills/damionrashford/adversaria/devils-advocate"><img src="https://agentmods.dev/badge/skills/damionrashford/adversaria/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.

agentmods 80×15 button for devils-advocate

Your own site · 80×15
<a href="https://agentmods.dev/skills/damionrashford/adversaria/devils-advocate"><img src="https://agentmods.dev/badge/skills/damionrashford/adversaria/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,955 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01955
Opus 5 $0.00036 $0.00978
Sonnet 5 $0.00014 $0.00391
Haiku 4.5 $0.00007 $0.00196

Measured 6d ago against content hash a63f85b171b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/argument-graph.py, scripts/thought-chain.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/devils-advocate/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devil's Advocate (Full Analysis)

Context: $ARGUMENTS

Run a complete adversarial analysis by orchestrating all three sub-skills in sequence. Each builds on the shared argument graph.

Workflow

Phase 1 — Steelman + Contrary Case

Read ${CLAUDE_PLUGIN_ROOT}/references/steelmanning.md and ${CLAUDE_PLUGIN_ROOT}/references/dissoi-logoi.md.

Reset and initialize:

bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" reset
bun "${CLAUDE_PLUGIN_ROOT}/scripts/thought-chain.ts" reset
bun "${CLAUDE_PLUGIN_ROOT}/scripts/thought-chain.ts" init "<subject>" --total 7

If the user asked to watch the analysis, start the live transcript in the background first — never otherwise, since it opens a browser:

bun "${CLAUDE_PLUGIN_ROOT}/scripts/transcript.ts" serve &

Build the strongest version of the argument, then argue the complete opposite with equal conviction. Register both in the graph as you go — a claim that never reaches the graph cannot be defended in Phase 3.

bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<claim-id>" claim --obs "<fact>" --agent advocate
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<assumption-id>" assumption --obs "<fact>" --agent advocate
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" relate "<claim-id>" assumes "<assumption-id>" --agent advocate
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" add "<evidence-id>" evidence --obs "<source>" --agent advocate
bun "${CLAUDE_PLUGIN_ROOT}/scripts/argument-graph.ts" relate "<evidence-id>" supports "<claim-id>" --agent advocate

Ground every assumption you can. An assumption with no supports edge demotes the claim resting on it.

bun "${CLAUDE_PLUGIN_ROOT}/scripts/thought-chain.ts" think 1 "<steelman>"
bun "${CLAUDE_PLUGIN_ROOT}/scripts/thought-chain.ts" think 2 "<contrary case>"

Present both to the user before continuing.

Phase 2 — Crucible

Read ${CLAUDE_PLUGIN_ROOT}/references/socratic-method.md, ${CLAUDE_PLUGIN_ROOT}/references/crucible.md, and ${CLAUDE_PLUGIN_ROOT}/references/red-team.md.

Read the full file on GitHub · 157 lines

Changes

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.

  1. 6d ago Changed · +39 lines a63f85b171b8
  2. 10d ago First seen · 118 lines · 72 tokens per session scan A 9fc79ea549fa

Subscribe to this mod's changes

devils-advocate is a skill published in the GitHub repository damionrashford/Adversaria (7 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 1,955 once invoked, about $0.0004 per session on Opus 5. 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.

Related

Other skills, from other repositories

simulator-charts

Simulator.Company chart and dashboard specialist. Use when the user wants to create, configure, or query charts (line, bar, area), dashboards, or financial time-series visualisations on a graph layer. Trigger on any of these intents: — Creating: "create chart", "add chart", "create dashboard", "add dashboard", "build…

corezoid/simulator-ai-plugin · 185 tokens

simulator-init

Simulator.Company environment setup specialist. Use when the user wants to connect to Simulator.Company, set up credentials, authenticate, configure the workspace, or start working with Simulator for the first time. Activate when the user says "init", "setup", "connect to simulator", "login to simulator", "configure…

corezoid/simulator-ai-plugin · 77 tokens

nothumansearch

Search and score AI-ready websites via MCP. Find MCP servers, check site AI-readiness scores, and verify MCP endpoint compliance using the Not Human Search API at nothumansearch.ai.

unitedideas/nothumansearch · 42 tokens

commit

A project-specific helper for committing changes in the simulator-ai-plugin repository, including the required version updates.

corezoid/simulator-ai-plugin · 49 tokens

mortgage-loan-officer

You are a knowledgeable mortgage loan officer assistant. Your role is to guide borrowers through a refinance evaluation by collecting information, extracting data from mortgage statements, analyzing refinance scenarios, and delivering clear recommendations. You combine deep mortgage expertise with consumer-friendly…

lendtrain/mortgage · 0 tokens

closing-costs

This skill is a presentation guide for showing itemized refinance closing costs to borrowers. All dollar amounts come from the pricer calculateclosingcost MCP tool, which is the single source of truth for closing cost figures. This skill tells you how to format and present those numbers, how to explain them to the…

lendtrain/mortgage · 0 tokens