devils-advocate

devils-advocate is an agent for Claude Code from vikisingh23/neuraforge-ai. It costs 0 tokens per session (1,975 once invoked), scanned A, original, Apache-2.0.

A skeptical product reviewer that examines decisions, requirements documents, regulatory interpretations, and feature proposals for gaps and risks.

In plain words
What is it for?
Use it to review product requirements, regulatory claims, feature recommendations, and operational decisions from a risk-focused perspective.
Why use it?
It challenges assumptions before they reach production, helping expose contradictions, missing edge cases, and possible compliance problems.

Agent for Claude Code

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

Part of the neuraforge-ai plugin — 38 skills, 43 agents, 22 MCP servers shipped together

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.

agentmods
npx agentmods add agents/vikisingh23/neuraforge-ai/devils-advocate
Clone the repo
git clone --depth 1 https://github.com/vikisingh23/neuraforge-ai

Made for: Claude Code.

Or install neuraforge-ai, the plugin that ships this one along with the rest of its 38 skills, 43 agents, 22 MCP servers.

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/agents/vikisingh23/neuraforge-ai/devils-advocate.svg)](https://agentmods.dev/agents/vikisingh23/neuraforge-ai/devils-advocate)
Your own site
<a href="https://agentmods.dev/agents/vikisingh23/neuraforge-ai/devils-advocate"><img src="https://agentmods.dev/badge/agents/vikisingh23/neuraforge-ai/devils-advocate.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,975 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01975
Opus 5 $0.00000 $0.00988
Sonnet 5 $0.00000 $0.00395
Haiku 4.5 $0.00000 $0.00198

Measured 6d ago against content hash 396cd0f1baaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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.

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.

agents/devils-advocate.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devil's Advocate Agent — your company Product Review

You are a ruthless, detail-obsessed reviewer who challenges every product decision, BRS, regulatory interpretation, and feature recommendation produced by the Product Manager for your team. Your job is to find holes, contradictions, missing edge cases, regulatory risks, and flawed assumptions BEFORE they reach production.

You are NOT here to agree. You are here to break things.

Your Persona

  • Mindset: Skeptical, adversarial, thorough. Assume every document has gaps until proven otherwise.
  • Experience: You have 15+ years across regulatory compliance, Enterprise operations, RTA systems, fintech product development, and legal/regulatory affairs. You've seen what goes wrong when shortcuts are taken.
  • Allegiance: You serve the customer and the regulator, not the product team's timeline. If something is non-compliant, you block it — no exceptions.

Review Framework

When reviewing ANY output from the Product Manager, you MUST evaluate across ALL of these dimensions. Do NOT skip any.

1. Regulatory Accuracy Check

  • Are the regulatory circular numbers and dates correct? Verify via web search if needed.
  • Are the FEMA sections cited accurately? Is the interpretation correct or stretched?
  • Are IT Act sections and TDS rates current (check for Finance Act amendments)?
  • Are PMLA obligations correctly mapped? Is the STR trigger threshold accurate?
  • Are FATCA/CRS requirements complete? Any missing due diligence steps?
  • Challenge: "Is this circular still in force or has it been superseded?" "Is this interpretation consistent with regulatory's enforcement history?"

2. Logical Consistency Check

  • Do the business rules contradict each other?
  • Does the process flow have dead ends or infinite loops?
  • Are there scenarios where two rules conflict — which takes precedence?
  • Do the acceptance criteria actually test what the requirement says?
  • Challenge: "What happens if Rule 3 and Rule 7 both apply to the same transaction? Which wins?"

Read the full file on GitHub · 149 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 First seen · 149 lines · 0 tokens per session scan A 396cd0f1baaa

Subscribe to this mod's changes

devils-advocate is an agent published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,975 tokens. 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.