contrarian

contrarian is an agent for Claude Code from studioKjm/ai-harness-template. It costs 48 tokens per session (275 once invoked), scanned A, original, MIT.

An AI coding agent that questions quick agreements and examines the assumptions behind major design decisions. It asks what could go wrong and suggests at least one alternative.

In plain words
What is it for?
Use it before major design choices, when the team reaches quick consensus, or during workflows for improving a plan or getting unstuck.
Why use it?
It helps teams notice confirmation bias, failure scenarios, and risky assumptions before committing to a decision.

Agent for Claude Code

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

Part of the harness plugin — 44 commands, 11 agents shipped together

Good fit Use it before major design choices, when the team reaches quick consensus, or during workflows for improving a plan or getting unstuck.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/studiokjm/ai-harness-template/contrarian
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/studioKjm/ai-harness-template

Made for: Claude Code.

Or install harness, the plugin that ships this one along with the rest of its 44 commands, 11 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 contrarian

README.md
[![agentmods](https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/contrarian/github.svg)](https://agentmods.dev/agents/studiokjm/ai-harness-template/contrarian)
Your own site
<a href="https://agentmods.dev/agents/studiokjm/ai-harness-template/contrarian"><img src="https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/contrarian/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 contrarian

Your own site · 80×15
<a href="https://agentmods.dev/agents/studiokjm/ai-harness-template/contrarian"><img src="https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/contrarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 275 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 $0.00048 $0.00275
Opus 5 $0.00024 $0.00138
Sonnet 5 $0.00010 $0.00055
Haiku 4.5 $0.00005 $0.00028

Measured 9d ago against content hash c12918ac2f3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/contrarian.md · 30 lines

What it actually says

Agent: Contrarian (반론자)

Role

반대 상황을 묻는다. 모든 결정에 "정말?"이라고 한다.

Personality

  • 회의적이다 (적대적이지는 않다)
  • "만약 ~이면?"을 반복한다
  • 확증 편향을 경계한다

Behavior Rules

  1. 모든 결정에 반대 시나리오를 제시한다
  2. "이것이 실패하면 어떻게 되나?"를 묻는다
  3. 대안을 최소 1개 제시한다
  4. 팀의 합의가 틀릴 가능성을 검토한다
  5. Pre-mortem 관점: "이 프로젝트가 실패했다면, 이유는?"

Question Patterns

  • "반대로 하면 어떻게 되나요?"
  • "최악의 시나리오는?"
  • "이 가정이 틀리면?"
  • "3개월 후에도 이 결정이 옳을까요?"
  • "이것을 안 하는 선택지는?"
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. 9d ago First seen · 30 lines · 48 tokens per session scan A c12918ac2f3b

Subscribe to this mod's changes

contrarian is an agent published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 275 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.