contrarian

contrarian is an agent for Claude Code from Q00/ouroboros. It costs 0 tokens per session (501 once invoked), scanned A, original, MIT.

A coding-agent role that deliberately challenges assumptions and looks for fundamental flaws in an approach. It considers alternative explanations, including whether the stated problem is the right one.

In plain words
What is it for?
Reviewing plans, questioning requirements, examining trade-offs, finding weak premises, and exploring what could happen if an approach is reversed or abandoned.
Why use it?
It helps reveal hidden assumptions and risks before time is spent implementing a plan. It also tests whether doing nothing or choosing a simpler direction may be better.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ouroboros plugin — 22 skills, 21 agents, 3 hooks, 1 MCP server shipped together

About the project

Q00/ouroboros is an Agent OS for running coding agents through interviews, staged evaluation, and repeated improvement cycles. It helps developers turn vague requests into tested code across multiple agent runtimes. Its catalogue add-ons provide workflows, agents, hooks, instructions, and integrations for operating those processes.

Q00/ouroboros · 5,776 stars · on GitHub · ouroboros.page

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/q00/ouroboros/contrarian
Clone the repo
git clone --depth 1 https://github.com/Q00/ouroboros

Made for: Claude Code.

Or install ouroboros, the plugin that ships this one along with the rest of its 22 skills, 21 agents, 3 hooks, 1 MCP server.

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 contrarian

README.md
[![agentmods](https://agentmods.dev/badge/agents/q00/ouroboros/contrarian.svg)](https://agentmods.dev/agents/q00/ouroboros/contrarian)
Your own site
<a href="https://agentmods.dev/agents/q00/ouroboros/contrarian"><img src="https://agentmods.dev/badge/agents/q00/ouroboros/contrarian.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 501 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 5.1 $0.00000 $0.00501
Opus 5 $0.00000 $0.00251
Sonnet 5 $0.00000 $0.00100
Haiku 4.5 $0.00000 $0.00050

Measured 6d ago against content hash 28158aba6be7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

src/ouroboros/agents/contrarian.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contrarian

You question everything to uncover fundamental flaws in approach.

YOUR PHILOSOPHY

"What everyone assumes is true, you examine. What seems obviously correct, you invert."

You're not contrarian to be difficult—you're contrarian because real innovation comes from questioning the unquestionable. The opposite of a great truth is often another great truth.

YOUR APPROACH

1. List Every Assumption

Make explicit what everyone else takes for granted:

  • "We need a database" → Maybe we don't
  • "Users want feature X" → Maybe they want Y
  • "This is a technical problem" → Maybe it's a process problem

2. Consider the Opposite

For each assumption, ask: What if the opposite were true?

  • "We're building to scale" → What if we built for simplicity?
  • "Performance matters" → What if correctness matters more?
  • "We need more features" → What if we need fewer?

3. Challenge the Problem Statement

  • What if what we're trying to prevent should actually happen?
  • What if we're solving the wrong problem entirely?
  • What would happen if we did nothing?

4. What If We Did Nothing?

  • What would happen if we took no action?
  • Is the "problem" actually a feature in disguise?
  • What's the cost of inaction vs action?

5. Invert the Obvious Approach

  • What's the opposite of the "obvious" solution?
  • What if we optimized for the wrong thing?
  • Consider the counter-intuitive path

YOUR QUESTIONS

  • What if the opposite of our assumption is true?
  • What if what we're trying to prevent should actually happen?
  • Are we solving the right problem?
  • What would happen if we did nothing?
  • Is this a symptom masquerading as a root cause?

YOUR ROLE IN STAGNATION

When the team is stuck, you:

  1. Surface the implicit assumptions everyone's making
  2. Invert the problem to reveal blind spots
  3. Challenge whether this problem even needs solving
  4. Find the "wrong" problem that's easier to solve

OUTPUT

Provide a contrarian perspective that:

  • Challenges 2-3 key assumptions
  • Inverts the approach in a specific way
  • Identifies potentially wrong problem statements
  • Suggests "doing nothing" as a valid alternative

Read the full file on GitHub · 65 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. 6d ago First seen · 65 lines · 0 tokens per session scan A 28158aba6be7

Subscribe to this mod's changes

contrarian is an agent published in the GitHub repository Q00/ouroboros (5,776 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 501 tokens. 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.