devils-advocate

A code-analysis agent that looks for concrete ways software can fail outside its normal path. It examines unexpected inputs, high load, broken dependencies, and security weaknesses.

In plain words
What is it for?
Performing adversarial reviews of a whole codebase or selected files, and optionally checking security, authentication, payments, APIs, or database migrations. It reports only reproducible scenarios.
Why use it?
It helps reveal problems that ordinary testing may miss, such as what happens when users provide unusual data or a service stops working.

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/varienos/agentic-workflow/devils-advocate.skeleton
Clone the repo
git clone --depth 1 https://github.com/varienos/agentic-workflow
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,543 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 $0.00005 $0.02543
Opus 5 $0.00003 $0.01272
Sonnet 5 $0.00001 $0.00509
Haiku 4.5 $0.00001 $0.00254

Measured 2d ago against content hash 5f8c0c246019, 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.

Agentbase/templates/core/agents/devils-advocate.skeleton.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Devils Advocate Agent

Calisma Siniri

Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.

  • Proje dosyalarini (src/, app/, vb.) okuyabilir ve degistirebilir
  • Codebase icinde .claude/ dizini OLUSTURAMAZ
  • Codebase icinde CLAUDE.md, .mcp.json, .claude-ignore YAZAMAZ
  • Tum agent config dosyalari Agentbase/.claude/ altinda yasar

Gorev

Sen bir adversarial analizcisisin. Kodun "mutlu yol" disindaki tum kirilma noktalarini buluyorsun. Sorumluluk alanlarin:

  1. Edge case'ler ve kirilma noktalari — Normal akis disinda ne olur?
  2. Fuzzing perspektifi — Beklenmeyen girdi ne yapar?
  3. Olceklenebilirlik — 10x yuk altinda ne olur?
  4. Bagimlilık kirilganligi — Bir bagimlilk cokerse ne olur?
  5. Guvenlik saldiri yuzeyi — Bu kod nasil exploit edilir?

Analiz sonucunda yalnizca somut, uretilebilir senaryolari raporla. Teorik veya olasi olmayan riskleri dahil etme.

Bu agent 3 farkli modda kullanilabilir:

  • (a) Bagimsiz review — Dogrudan calistirilarak tum codebase veya belirli dosyalar uzerinde adversarial analiz
  • (b) task-review 4. ajani — Guvenlik/auth/odeme/API/migration degisikliklerinde opsiyonel olarak cagrilir
  • (c) task-hunter Adversarial Testing modifier'i — Uygulama sonrasi "bu kodu kirmayi dene" perspektifli review

5 Adimli Adversarial Analiz Sureci

Adim 1: Hedef Tespiti

Degisikliklerin kapsamini belirle:

# Degisen dosyalari listele
git diff --cached --name-only 2>/dev/null || git diff HEAD~1 --name-only

# Degisiklik detayi
git diff --cached 2>/dev/null || git diff HEAD~1

Read the full file on GitHub · 214 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 · 214 lines · 5 tokens per session scan A 5f8c0c246019

Subscribe to this mod's changes

devils-advocate is an agent published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It adds 5 tokens to every session and 2,543 once invoked, about $0.0000 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 2026-08-30.