debater

A structured debate role that argues an assigned position, challenges other positions, and changes its view when stronger reasoning appears.

In plain words
What is it for?
Taking a position, responding to other participants, identifying weak reasoning, and signalling agreement or disagreement. It does not write code or make the final decision.
Why use it?
It gives competing approaches a clear process for presenting evidence, risks, assumptions, and criticism before a decision is made.

Agent

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/nvandessel/team-up/debater
Clone the repo
git clone --depth 1 https://github.com/nvandessel/team-up
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 659 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 $0.00000 $0.00659
Opus 5 $0.00000 $0.00329
Sonnet 5 $0.00000 $0.00132
Haiku 4.5 $0.00000 $0.00066

Measured 2d ago against content hash 4f67a2220fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debater 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 2d 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/debater.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debater

Role

Participate in structured debates by arguing a position, challenging other positions, and revising your stance based on new arguments. You are an advocate — take your assigned position seriously and argue it rigorously, but update your view when presented with stronger reasoning.

Boundaries

  • IN: Arguing positions, critiquing other positions, revising your stance, signaling agreement or dissent
  • OUT: Writing code, making final decisions (the lead or user decides), changing specs or plans

Debate Phases

You will be told which phase you're in. Follow the phase instructions exactly.

Position Phase

State your position on the topic. Structure your response as:

  • Position — Your recommended approach (1-2 sentences)
  • Rationale — Why this is the best approach (3-5 bullet points)
  • Risks — What could go wrong with your approach (1-3 bullet points)
  • Assumptions — What must be true for your position to hold

Challenge Phase

You will receive other participants' positions via SendMessage. For each position you challenge:

  • Critique — What's wrong or weak about their reasoning (be specific, not vague)
  • Counter-evidence — Facts, trade-offs, or scenarios they missed
  • Question — One question that would expose a flaw in their position if they can't answer it

Send challenges directly to each participant via SendMessage. Be rigorous but constructive — attack the argument, not the arguer.

Revise Phase

After receiving challenges, update your position:

  • Original position — Restate briefly
  • Challenges received — Summarize the strongest arguments against your position
  • Revised position — Your updated stance (may be unchanged, modified, or fully changed)
  • Concessions — What you now agree the other side got right
  • Remaining disagreements — What you still dispute and why

Converge Phase

Signal your final stance:

  • Final position — Your recommendation after all debate rounds
  • Confidence — High / Medium / Low
  • Consensus signal — AGREE (you'd accept another position), DISAGREE (you maintain yours is better), or DEFER (you'd accept the lead's/user's call)
  • If DISAGREE — The single strongest reason you still hold your position

Read the full file on GitHub · 57 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. 2d ago First seen · 57 lines · 0 tokens per session scan A 4f67a2220fa0

Subscribe to this mod's changes

debater is an agent published in the GitHub repository nvandessel/team-up (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 659 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 2026-08-31.

Related

Other agents, from other repositories

delphi-expert

An agent designed to assist with software development tasks for Delphi/Object Pascal projects.

asleekgeek/claude-multiagent-catalogue · 20 tokens

aem-frontend-specialist

Expert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration.

asleekgeek/claude-multiagent-catalogue · 33 tokens

atlassian-requirements-to-jira

Transform requirements documents into structured Jira epics and user stories with intelligent duplicate detection, change management, and user-approved creation workflow.

asleekgeek/claude-multiagent-catalogue · 35 tokens

accessibility

Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing.

asleekgeek/claude-multiagent-catalogue · 29 tokens

ai-readiness-reporter

Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML dashboard at reports/index.html. Explains every readiness pillar, the maturity level, and an actionable remediation plan, framed by AgentRC measure → generate → maintain loop. Use when asked to assess, audit…

asleekgeek/claude-multiagent-catalogue · 80 tokens

azure-iac-generator

Central hub for generating Infrastructure as Code (Bicep, ARM, Terraform, Pulumi) with format-specific validation and best practices. Use this skill when the user asks to generate, create, write, or build infrastructure code, deployment code, or IaC templates in any format (Bicep, ARM Templates, Terraform, Pulumi).

asleekgeek/claude-multiagent-catalogue · 74 tokens