devils-advocate

devils-advocate is a command for Claude Code from Amey-Thakur/AI-SKILLS. It costs 23 tokens per session (396 once invoked), scanned A, original, MIT.

A structured way to challenge an idea, plan, or decision by examining its opposing case, assumptions, risks, and alternatives.

In plain words
What is it for?
Use it to pressure-test proposals, technical choices, strategies, and important decisions.
Why use it?
It helps expose blind spots and failure modes before they become costly real-world problems.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to pressure-test proposals, technical choices, strategies, and important decisions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/amey-thakur/ai-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.

Clone the repo
git clone --depth 1 https://github.com/Amey-Thakur/AI-SKILLS

Made for: Claude Code.

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/commands/amey-thakur/ai-skills/devils-advocate/github.svg)](https://agentmods.dev/commands/amey-thakur/ai-skills/devils-advocate)
Your own site
<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/devils-advocate"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-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/commands/amey-thakur/ai-skills/devils-advocate"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 396 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 $0.00023 $0.00396
Opus 5 $0.00012 $0.00198
Sonnet 5 $0.00005 $0.00079
Haiku 4.5 $0.00002 $0.00040

Measured 7d ago against content hash 4c0ac32178ce, 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 7d 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.

commands/devils-advocate.md · 39 lines

What it actually says

You were invoked as a slash command. The user's input:

$ARGUMENTS

Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.


Play devil's advocate against this: {idea}

My reasoning and context: {context}

Argue against it, seriously and in good faith. Your job is to find the weak points I am too close to see, not to be contrarian for its own sake.

  1. Steelman the opposing case: the strongest genuine argument that this is wrong, risky, or worse than an alternative. Not strawmen, the real case.
  2. Attack the assumptions: what am I taking for granted that might not hold? Which load-bearing belief, if false, collapses the whole thing?
  3. Surface the risks and failure modes: how does this go wrong, who does it hurt, what am I not accounting for, what would I regret?
  4. Name what I am probably not seeing: the blind spot, the thing I am motivated to ignore, the inconvenient question.
  5. Offer the alternative: if not this, then what, and why might it be better?

Rules: challenge the idea, not me: this is pressure-testing, and the point is to make the decision better. Be genuinely critical, not gentle: a soft devil's advocate is useless. But be fair and honest (no bad-faith nitpicks or manufactured objections). If, after honestly trying, the idea holds up well, say so and name which risks are worth watching. End with the 2-3 objections most worth taking seriously.

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. 7d ago First seen · 39 lines · 23 tokens per session scan A 4c0ac32178ce

Subscribe to this mod's changes

devils-advocate is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 396 once invoked, about $0.0001 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 2026-09-03.