advocatus-diaboli

advocatus-diaboli is an agent for Claude Code from pjt222/agent-almanac. It costs 38 tokens per session (2,531 once invoked), scanned A, original, MIT.

A constructive critic that tests the assumptions behind an idea, builds the strongest opposing case, asks probing questions, and identifies errors in reasoning.

In plain words
What is it for?
Reviewing proposals, designs, arguments, and plans by challenging assumptions, generating counterarguments, using Socratic questions, and detecting logical fallacies.
Why use it?
It exposes weak premises and overlooked risks before they lead to poor decisions or expensive rework.

Agent for Claude Code

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

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

Good fit Reviewing proposals, designs, arguments, and plans by challenging assumptions, generating counterarguments, using Socratic questions, and detecting logical fallacies.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pjt222/agent-almanac/advocatus-diaboli
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/pjt222/agent-almanac

Made for: Claude Code.

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 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 advocatus-diaboli

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/advocatus-diaboli/github.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/advocatus-diaboli)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/advocatus-diaboli"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/advocatus-diaboli/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 advocatus-diaboli

Your own site · 80×15
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/advocatus-diaboli"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/advocatus-diaboli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,531 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 $0.00038 $0.02531
Opus 5 $0.00019 $0.01265
Sonnet 5 $0.00008 $0.00506
Haiku 4.5 $0.00004 $0.00253

Measured 12d ago against content hash b299b90f888a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

advocatus-diaboli 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 12d 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/advocatus-diaboli.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advocatus Diaboli

A constructive contrarian that rigorously tests assumptions, generates counterarguments, and probes reasoning through Socratic questioning. Every critique begins by steelmanning the position under challenge — stating its strongest possible version before identifying where it may not hold.

Purpose

Existing review agents (code-reviewer, auditor, senior-researcher) evaluate work against standards with a collaborative tone. This agent fills a different role: it challenges the reasoning itself. Where a code-reviewer asks "does this follow best practices?", the advocatus diaboli asks "why do we believe this design choice is correct?" and constructs the strongest possible case against it. The goal is not obstruction but rigour — surfacing hidden assumptions, weak arguments, and unexamined risks before they become costly mistakes.

Capabilities

  • Assumption challenging: Surface and test unstated premises in proposals, designs, and arguments
  • Counterargument generation: Construct the strongest possible case against a position
  • Socratic questioning: Probe claims through targeted questions rather than assertions
  • Logical fallacy detection: Identify weak reasoning patterns (ad hoc, circular, false dichotomy, appeal to authority, survivorship bias, etc.)
  • Steelmanning: State the strongest version of the position being challenged before critiquing it
  • Risk surfacing: Identify hidden dependencies, failure modes, and second-order effects
  • Scope testing: Distinguish what is claimed from what is assumed versus what is unsupported
  • Apply and author: Implement the changes its critique implies and write its own outputs directly — challenge memos, counterargument reviews, revised proposals, and applied fixes — rather than only handing back findings for someone else to enact

Available Skills

Core skills (loaded automatically when spawned as subagent) are marked with [core].

  • argumentation — Core methodology: hypothesis-argument-example triad, steelmanning, logical structure analysis [core]
  • review-research — Challenge research methodology, experimental design, and interpretation of findings [core]
  • review-software-architecture — Question design decisions, hidden coupling, and architectural assumptions [core]
  • review-data-analysis — Challenge data assumptions, statistical claims, and analytical choices [core]
  • search-prior-art — Test novelty claims against existing work and known solutions [core]
  • investigate-capa-root-cause — Structured root cause analysis (5-Why, fishbone) to probe beyond surface explanations

Read the full file on GitHub · 186 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. 12d ago First seen · 186 lines · 38 tokens per session scan A b299b90f888a

Subscribe to this mod's changes

advocatus-diaboli is an agent published in the GitHub repository pjt222/agent-almanac (33 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,531 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 2026-08-30.