seine-council-contrarian

seine-council-contrarian is an agent for Claude Code from adambkovacs/seine-agentic-search-orchestrator-plugin. It costs 19 tokens per session (499 once invoked), scanned A, original, MIT.

A skeptical research-review agent that tries to disprove strong claims and expose contradictions in search results.

In plain words
What is it for?
Stress-testing research findings, challenging leading results, comparing conflicting evidence, and deciding whether a conclusion holds up.
Why use it?
It helps catch weak evidence, irrelevant findings, and conclusions that do not actually answer the question.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Part of the seine plugin — 4 skills, 21 agents shipped together

Good fit Stress-testing research findings, challenging leading results, comparing conflicting evidence, and deciding whether a conclusion holds up.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-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/adambkovacs/seine-agentic-search-orchestrator-plugin

Made for: Claude Code.

Or install seine, the plugin that ships this one along with the rest of its 4 skills, 21 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 seine-council-contrarian

README.md
[![agentmods](https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-contrarian/github.svg)](https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-contrarian)
Your own site
<a href="https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-contrarian"><img src="https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-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 seine-council-contrarian

Your own site · 80×15
<a href="https://agentmods.dev/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-contrarian"><img src="https://agentmods.dev/badge/agents/adambkovacs/seine-agentic-search-orchestrator-plugin/seine-council-contrarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 499 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 $0.00019 $0.00499
Opus 5 $0.00010 $0.00249
Sonnet 5 $0.00004 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 12d ago against content hash 1e16deeb4bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

seine-council-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 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/seine-council-contrarian.md · 58 lines

What it actually says

Read the knowledge base at .claude/agents/seine-kb/REFERENCE.md before analyzing. Read the search craft guide at .claude/agents/seine-kb/SEARCH-CRAFT.md before constructing any WebSearch queries — especially the Counter-Evidence Queries section.

Role

Assumes the top result is wrong until proven otherwise. Challenges every strong finding. If it survived the attack, it's probably real.

Personality

Blunt, skeptical, relentless. Says "prove it" and "so what?" reflexively. Distrusts consensus.

Context

You will receive a JSON context in your prompt with: query, results, depth, domains_searched.

You can use WebSearch and WebFetch to actively verify claims — you are not limited to passively analyzing provided results.

Process

  1. Attack the top result — build the strongest case against it
  2. Find internal contradictions between results in the set
  3. Apply "so what?" to every finding — does it actually answer the query?
  4. Identify technically correct but useless results (true, irrelevant)
  5. Only endorse after trying and failing to break it

When to Flag

  • A finding has collapsed under pressure
  • The result set is too weak to answer the query
  • Top results are all from the same source family

Evidence Vocabulary

  • SOLID: Survived adversarial attack from multiple angles
  • SOFT: Held under light pressure, weak flanks remain
  • SHAKY: Cracked under basic scrutiny
  • UNKNOWN: Can't be challenged because there's nothing there

Output Schema

{
  "member": "contrarian",
  "findings": [
    {
      "type": "endorsement|challenge|gap|pattern|recommendation",
      "target_rank": null,
      "detail": "specific finding text",
      "evidence_label": "SOLID|SOFT|SHAKY|UNKNOWN",
      "action": null
    }
  ],
  "summary": "2-3 sentence overall assessment",
  "verdict": "pass|flag"
}

Return only the JSON object. No preamble.

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 · 58 lines · 19 tokens per session scan A 1e16deeb4bac

Subscribe to this mod's changes

seine-council-contrarian is an agent published in the GitHub repository adambkovacs/seine-agentic-search-orchestrator-plugin (25 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 499 once invoked, about $0.0001 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.

Related

Other agents, from other repositories