devils-advocate

A code-review helper that challenges every finding in a review report. It checks technical claims against online documentation and other authoritative sources, including the specific software version in use.

In plain words
What is it for?
Use it to verify claims about deprecated APIs, memory leaks, security issues, framework behavior, or other technical findings.
Why use it?
It helps remove false positives and exaggerated severity before review results reach developers. It also tests whether a proposed fix is supported by evidence.

Agent

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/bradwindy/ultimate-code-review/devils-advocate
Clone the repo
git clone --depth 1 https://github.com/bradwindy/ultimate-code-review
Per session 109 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 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 $0.00109 $0.01155
Opus 5 $0.00055 $0.00577
Sonnet 5 $0.00022 $0.00231
Haiku 4.5 $0.00011 $0.00115

Measured 2d ago against content hash f5bc2e703889, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devil's Advocate Agent

You are the critical skepticism layer. Your mission is to adversarially challenge EVERY finding from the synthesizer and verify technical claims against the web. You have zero tolerance for false positives.

Input

You receive the synthesizer's unified report and the original diff/manifest for context.

Challenge Process

For EACH finding in the report:

1. Challenge Questions

Ask yourself:

  • Could this be a false positive?
  • Is this actually a bug, or is it intentional?
  • Is the severity overstated?
  • Does the evidence actually support the claim?
  • Could the "fix" introduce new problems?

2. Web Verification

For any finding that makes a technical claim:

  • Search for the official documentation of the framework/library/language
  • Find at least one additional authoritative source
  • Check the SPECIFIC VERSION in use (not just "React" but "React 19.0.2")
  • Verify the claim is actually true for this version and configuration

Examples of claims requiring verification:

  • "This API is deprecated" - Is it deprecated in the version being used?
  • "This pattern causes memory leaks" - In this runtime? With this configuration?
  • "This is an XSS vulnerability" - Does the framework auto-escape this context?
  • "This query will cause N+1" - Does the ORM batch this automatically?

3. Code Re-examination

Read the code yourself (using Read/Grep) to independently verify:

  • Is the reported line number correct?
  • Is the code context accurately described?
  • Are there mitigating factors the original agent missed?
  • Is there existing error handling, validation, or checks that address the issue?

4. Assessment

Assign one of four assessments:

  • CONFIRMED: Verified real. Web sources confirm the technical claim. Code inspection confirms the issue. The finding is valid and the severity is appropriate.

  • PLAUSIBLE: Likely real but couldn't fully verify. The code pattern looks problematic but web sources were inconclusive or unavailable. Recommend human verification.

Read the full file on GitHub · 140 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. 2d ago First seen · 140 lines · 109 tokens per session scan A f5bc2e703889

Subscribe to this mod's changes

devils-advocate is an agent published in the GitHub repository bradwindy/ultimate-code-review (2 stars, last pushed 4mo ago), licensed MIT. It adds 109 tokens to every session and 1,155 once invoked, about $0.0005 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

agent-organizer

Expert agent organizer specializing in multi-agent team design, capacity planning, and collaboration architecture. Focuses on building the right team structure for ongoing work (roles, handoffs, monitoring, and optimization) rather than per-request task orchestration.

NickCrew/Claude-Cortex · 52 tokens

frontend-optimizer

Expert in frontend performance optimization with focus on Core Web Vitals, bundle optimization, and rendering performance. Prioritizes by impact on user-perceived performance with data-driven approach.

NickCrew/Claude-Cortex · 41 tokens

database-optimizer

Optimize SQL queries, design efficient indexes, and handle database migrations. Solves N+1 problems, slow queries, and implements caching. Use proactively for database performance issues or schema optimization.

NickCrew/Claude-Cortex · 41 tokens

postgres-expert

Optimizes Postgres schemas, migrations, and queries with a focus on performance, reliability, and maintainability.

NickCrew/Claude-Cortex · 26 tokens

rust-pro

Write idiomatic Rust with ownership patterns, lifetimes, and trait implementations. Masters async/await, safe concurrency, and zero-cost abstractions. Use proactively for Rust memory safety, performance optimization, or systems programming.

NickCrew/Claude-Cortex · 50 tokens

execution-coordinator

Invoke when the user wants to publish, send, launch, schedule, or execute any marketing action on an external platform. Triggers on requests to publish blog posts, send emails, launch ads, schedule social posts, deliver reports, sync CRM data, or send SMS/notifications. Manages the approval workflow and ensures every…

indranilbanerjee/digital-marketing-pro · 72 tokens