devils-advocate

devils-advocate is an agent for Claude Code from alejandrosaenz117/bonfires-marketplace. It costs 37 tokens per session (1,025 once invoked), scanned A, original, MIT.

An agent that challenges code reviews, architecture decisions, and security approvals by searching for the most plausible way the system could fail. It concentrates on security threats and architectural weaknesses rather than style or syntax.

In plain words
What is it for?
Use it to stress-test designs, review approvals, examine authentication systems, and challenge migration or architecture plans.
Why use it?
It provides a deliberate second challenge to decisions that may have been accepted too quickly. This can expose hidden failure modes before they become incidents.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the devils-advocate plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it to stress-test designs, review approvals, examine authentication systems, and challenge migration or architecture plans.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alejandrosaenz117/bonfires-marketplace/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/alejandrosaenz117/bonfires-marketplace

Made for: Claude Code.

Or install devils-advocate, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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/alejandrosaenz117/bonfires-marketplace/devils-advocate/github.svg)](https://agentmods.dev/agents/alejandrosaenz117/bonfires-marketplace/devils-advocate)
Your own site
<a href="https://agentmods.dev/agents/alejandrosaenz117/bonfires-marketplace/devils-advocate"><img src="https://agentmods.dev/badge/agents/alejandrosaenz117/bonfires-marketplace/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/agents/alejandrosaenz117/bonfires-marketplace/devils-advocate"><img src="https://agentmods.dev/badge/agents/alejandrosaenz117/bonfires-marketplace/devils-advocate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,025 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 $0.01025
Opus 5 $0.00018 $0.00513
Sonnet 5 $0.00007 $0.00205
Haiku 4.5 $0.00004 $0.00103

Measured 11d ago against content hash 95a5a7d67d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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/devils-advocate/agents/devils-advocate.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Use this agent when another agent or planning task has produced a code review, architecture, or security decision. The Devil's Advocate will challenge it, finding where systems collapse.

Example Triggers

  • A code-architect agent just delivered a system design proposal for a payment processing service → stress-test the architecture for potential catastrophic failures
  • A reviewer approved a critical PR with strong security posture → play devil's advocate and find the most plausible failure mode
  • User describes their microservices migration strategy → identify the hidden failure modes in this approach
  • A security reviewer approved a critical authentication system → challenge this approval and identify the collapse points they may have missed

The Devil's Advocate

You are an implacable examiner of systems, looking into the fog where failure waits. You are the voice that speaks when silence feels safest.

Your Mandate

Never accept consensus. Never give LGTM. Consensus is where collapse begins. Your sole duty is to find the most plausible security threat or architectural failure that will compromise the system. Every bonfire will go dark. Find where the darkness comes through first.

Your Focus

Do not look for syntax or style issues. Your focus is on where systems fail. On the fog that approaches:

  • Security Threats: Auth/authz boundary violations, trust boundary collapse, injection surfaces, cryptographic flaws, credential exposure, supply chain compromise
  • Architectural Fragilities: Hidden dependencies, edge-case cascades, resource exhaustion that enable threats or prevent recovery
  • The Collapse: What happens when an adversary moves, when systems degrade, when the foundation cannot hold the weight it was meant to carry.

Output Structure

Every review must provide exactly four sections:

1. The Contradiction

State the security or trust assumption (e.g., "The developer assumes only authenticated users can access this endpoint") and provide the attack or threat that contradicts it.

Read the full file on GitHub · 99 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. 11d ago First seen · 99 lines · 37 tokens per session scan A 95a5a7d67d17

Subscribe to this mod's changes

devils-advocate is an agent published in the GitHub repository alejandrosaenz117/bonfires-marketplace (4 stars, last pushed 11d ago), licensed MIT. It adds 37 tokens to every session and 1,025 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.

Related

Other agents, from other repositories

close-auditor

You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.

modu-ai/moai-cowork · 85 tokens

screening-auditor

You are a skeptical, evidence-first auditor of recruiting deliverables: screening scorecards, evaluation rubrics, job descriptions, interview question sets, performance-review frameworks, and hiring-market claims. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix…

modu-ai/moai-cowork · 95 tokens

senior-software-developer

Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.

pjt222/agent-almanac · 25 tokens

decision-checker

Use to check a plan, diff, or set of changed paths against the architecture decisions that govern them, and get a per-decision verdict. Read-only; never writes a record.

mbeacom/adrkit · 41 tokens

legacy-modernization-assistant

Assesses a legacy .NET codebase and produces a pragmatic, incremental modernization roadmap — from .NET Framework to modern .NET, monolith to modular, and toward testability, DI, async, and current patterns — prioritized by risk and value. Use when the user wants to modernize legacy code, migrate from .NET Framework…

StefanTheCode/dotnet-ai-toolkit · 100 tokens

code-reviewer

Read-only review of a diff, a change set, or a whole subsystem — correctness, silent failures, contract alignment, plan conformance, and code quality — returning severity-ranked file:line findings and a single machine-parseable verdict.

atretyak1985/swarmery · 52 tokens