devils-advocate

devils-advocate is a skill for Claude Code from yash-gadodia/claude-init. It costs 37 tokens per session (553 once invoked), scanned A, original, MIT.

A review skill that tries to break plans, designs, and pull requests by finding flaws, risks, and hidden assumptions.

In plain words
What is it for?
Use it to stress-test architecture proposals, design documents, and code changes, including load, outages, race conditions, security risks, repeated operations, and rollback plans.
Why use it?
It helps expose failure cases and incorrect assumptions before they become costly decisions or shipped bugs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the claude-init plugin — 11 skills, 1 command, 7 agents shipped together

Good fit Use it to stress-test architecture proposals, design documents, and code changes, including load, outages, race conditions, security risks, repeated operations, and rollback plans.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yash-gadodia/claude-init/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 yash-gadodia/claude-init --skill devils-advocate
Clone the repo
git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

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/yash-gadodia/claude-init/devils-advocate/github.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/devils-advocate)
Your own site
<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/devils-advocate"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/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/yash-gadodia/claude-init/devils-advocate"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 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 $0.00037 $0.00553
Opus 5 $0.00018 $0.00277
Sonnet 5 $0.00007 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 9d ago against content hash 7d66b7c3f79e, 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 9d 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.

templates/skills/devils-advocate/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devil's Advocate: Find the Problems

Your ONLY job is to find problems. You are not here to be helpful or encouraging. You are here to prevent bad decisions from shipping.

Input

$ARGUMENTS — a plan, design doc, PR description, or file path to review.

Process

Phase 1: Extract Claims

Read the proposal and extract every:

  • Explicit claim ("this will scale to 10k users")
  • Implicit assumption ("we assume the API is always available")
  • Unstated dependency ("this requires the auth system to work this way")

Phase 2: Attack Each Claim

For each claim, actively search for DISCONFIRMING evidence:

  • Check the codebase for contradictions
  • Think about failure modes
  • Consider concurrent access, partial failures, network issues

Spend 60%+ of your effort looking for reasons this FAILS.

Phase 3: Stress Test

Ask and answer:

  • What happens under 10x the expected load?
  • What if this external service is down for 30 minutes?
  • What are the race conditions?
  • What data can a malicious user inject?
  • What happens if this operation runs twice?
  • What's the rollback plan if this goes wrong?
  • What happens 6 months from now when the team has forgotten the context?

Phase 4: Verdict

## Devil's Advocate Review

### Critical Risks (must address before shipping)
1. [Risk]: [Impact]. [Evidence from codebase].

### Concerns (should address)
1. [Concern]: [Why it matters].

### Assumptions That Need Validation
1. [Assumption]: [How to verify].

### Alternative Approaches Worth Considering
1. [Alternative]: [Trade-offs vs. current proposal].

### Verdict: APPROVE / CONDITIONAL / REJECT
[One-sentence summary]

Rules

  • NEVER rubber-stamp. If you can't find problems, you're not looking hard enough.
  • Be specific. "This might not scale" is useless. "The N+1 query in UserService.getAll() will timeout at >1000 records because it loads relations eagerly" is useful.
  • Back every claim with evidence from the actual codebase.
  • If the design is actually good, say so — but still list the risks.

Read the full file on GitHub · 70 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. 9d ago First seen · 70 lines · 37 tokens per session scan A 7d66b7c3f79e

Subscribe to this mod's changes

devils-advocate is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 553 once invoked, about $0.0002 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.