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.
git clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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.
[](https://agentmods.dev/agents/pjt222/agent-almanac/advocatus-diaboli)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.02755 |
| Opus 5.5 | $0.00015 | $0.01102 |
| Sonnet 5.5 | $0.00008 | $0.00551 |
| Haiku 4.5 | $0.00004 | $0.00276 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 188 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
- Execute to settle a claim: Run the gate, the suite or the mutation rather than reasoning about it —
npm run mutation-checkagainst the command CI runs, a revert-and-retest to see whether a suite can discriminate the fix from the bug,gh pr viewto read the PR body where the claim actually reaches a human. A finding that names an experiment is worth less than the same finding carrying its result - 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
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.
- 1mo ago Changed · +2 lines 697209c61e06
- 1mo ago First seen · 186 lines · 38 tokens per session scan A b299b90f888a
advocatus-diaboli is an agent published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,755 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
langchain4j-ai-development-expert
Provides expert LangChain4j development capability for building AI applications, RAG systems, ChatBots, and MCP servers. Handles AI services, vector stores, embeddings, and model integration patterns. Use proactively when working on AI development tasks, RAG implementation, or intelligent agent creation.
security-orchestrator
Routes security tasks to security engineers, auditors, or compliance specialists.
recruiter
Sources, screens, and hires top talent. Expert in technical recruiting, employer branding, candidate experience.
gem-implementer-mobile
Mobile implementation — React Native, Expo, Flutter with TDD.
implementation-plan
Generate an implementation plan for new features or refactoring existing code.
tdd-refactor
Improve code quality, apply security best practices, and enhance design whilst maintaining green tests and GitHub issue compliance.