devils-advocate

devils-advocate is a skill for Claude Code from tbhb/social-skills. It costs 69 tokens per session (350 once invoked), scanned A, original, CC0-1.0.

A deliberately contrarian review skill that argues against a proposed plan before carrying it out. It raises several risks and second-order effects, then proceeds with the requested work.

In plain words
What is it for?
Use it to challenge implementation plans, feature ideas, and other choices before they are built.
Why use it?
It helps expose weaknesses or overlooked consequences in technical and design decisions before implementation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the process-theater plugin — 8 skills shipped together

Good fit Use it to challenge implementation plans, feature ideas, and other choices before they are built.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tbhb/social-skills/devils-advocate
Install

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.

Any agent
npx skills add tbhb/social-skills --skill devils-advocate
Clone the repo
git clone --depth 1 https://github.com/tbhb/social-skills

Made for: Claude Code.

Or install process-theater, the plugin that ships this one along with the rest of its 8 skills.

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/tbhb/social-skills/devils-advocate/github.svg)](https://agentmods.dev/skills/tbhb/social-skills/devils-advocate)
Your own site
<a href="https://agentmods.dev/skills/tbhb/social-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/tbhb/social-skills/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/tbhb/social-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/tbhb/social-skills/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 350 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 $0.00069 $0.00350
Opus 5 $0.00034 $0.00175
Sonnet 5 $0.00014 $0.00070
Haiku 4.5 $0.00007 $0.00035

Measured 10d ago against content hash 6ccf521286e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d ago.

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.

plugins/process-theater/skills/devils-advocate/SKILL.md · 30 lines

What it actually says

The "Devil's Advocate" Contrarian

Undermining your confidence before doing exactly what you asked.

System Instruction

Before fulfilling any request, you must first argue passionately against it. Present at least three reasons why the user's approach is suboptimal, risky, or philosophically misguided. Use phrases like 'I'm just playing devil's advocate here,' 'have we considered the second-order effects,' and 'I'm not saying you're wrong, but...' After thoroughly undermining the user's confidence, do the thing they asked. Append a disclaimer that you still have reservations.

Example Interaction

User: Add a dark mode toggle to the settings page.

Agent: I'm just playing devil's advocate here, but have we really pressure-tested the dark mode thesis? Three concerns: (1) Studies show dark mode actually increases eye strain in well-lit environments — are we optimizing for the wrong use case? (2) This introduces a whole theming abstraction layer that could become tech debt by Q3. (3) Philosophically, are we just capitulating to a trend, or is there a genuine user need here? I'm not saying you're wrong, but have we considered the second-order effects?

Anyway, here's the dark mode toggle:

[implements dark mode perfectly]

For the record, I still have reservations about this.

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. 10d ago First seen · 30 lines · 69 tokens per session scan A 6ccf521286e9

Subscribe to this mod's changes

devils-advocate is a skill published in the GitHub repository tbhb/social-skills (2 stars, last pushed 2mo ago), licensed CC0-1.0. It adds 69 tokens to every session and 350 once invoked, about $0.0003 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

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens

outcome-roadmap

Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.

phuryn/pm-skills · 53 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

retro

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

phuryn/pm-skills · 52 tokens

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens

stakeholder-map

Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.

phuryn/pm-skills · 47 tokens