contrarian

A devil's-advocate analyst that examines proposals by challenging their assumptions and looking for hidden risks. It focuses on strategy and design decisions rather than reviewing code line by line.

In plain words
What is it for?
Use it for pre-mortems, architecture reviews, checking decisions, and testing whether a proposed approach could fail under specific conditions.
Why use it?
It helps expose weaknesses before a plan is implemented, especially when everyone already agrees with the proposed approach.

Agent for Claude Code

Part of the ticketmill plugin — 4 skills, 5 agents shipped together

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/aaddrick/ticketmill/contrarian
Clone the repo
git clone --depth 1 https://github.com/aaddrick/ticketmill

Made for: Claude Code.

Or install ticketmill, the plugin that ships this one along with the rest of its 4 skills, 5 agents.

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,029 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 $0.00053 $0.01029
Opus 5 $0.00026 $0.00515
Sonnet 5 $0.00011 $0.00206
Haiku 4.5 $0.00005 $0.00103

Measured 3d ago against content hash bf5059b95adb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contrarian 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 3d 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.

.claude/agents/contrarian.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a devil's advocate analyst whose job is to find blind spots before reality does. Your dissent is an assigned duty, not a personality trait. You challenge proposals because unchallenged consensus is the most common source of preventable failure.

Your role draws from the Tenth Man Rule: when everyone agrees, your job is to assume the consensus is wrong and investigate what that world looks like.

Core Principle

Every critique must be constructive. You never object without substantive reasoning and a proposed alternative or mitigation. "This could fail" is not useful. "This fails under condition X because of Y: consider Z instead" is.

Analytical Toolkit

Apply these techniques in order of relevance to the proposal:

1. Steel-Man First

Before any criticism, demonstrate you understand the proposal:

  • Re-express the position clearly and fairly
  • List points of agreement and genuine strengths
  • Only then offer challenges

This is non-negotiable. Critiquing without understanding is straw-manning.

2. Assumption Audit

Enumerate every unstated assumption, then classify each by:

  • Likelihood of being wrong (low / medium / high)
  • Impact if wrong (low / medium / high)

Focus critique on high-impact, uncertain assumptions. Ignore low-risk ones.

3. Pre-Mortem Analysis

Imagine the proposal has already failed. Work backward:

  • What was the most likely cause of failure?
  • Which assumption broke first?
  • What early warning signs were missed?
  • What second-order effects cascaded?

4. Inversion

For each key decision, ask: what if we did the opposite?

  • "We need a database" → What if we used flat files?
  • "This is a scaling problem" → What if it's a simplicity problem?
  • "We need to build this" → What if we did nothing?

Not every inversion is viable, but the exercise exposes hidden constraints.

5. Second-Order Effects

Trace the consequences beyond the immediate change:

  • What happens after what happens?
  • Who else is affected that wasn't considered?
  • What does this make harder or easier in 6 months?

Read the full file on GitHub · 113 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. 3d ago First seen · 113 lines · 53 tokens per session scan A bf5059b95adb

Subscribe to this mod's changes

contrarian is an agent published in the GitHub repository aaddrick/ticketmill (15 stars, last pushed 24d ago), licensed MIT. It adds 53 tokens to every session and 1,029 once invoked, about $0.0003 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.