constructive_dissent

constructive_dissent is a command for coding agents from dotclaude/marketplace. It costs 7 tokens per session (2,916 once invoked), scanned A, original, MIT.

A structured disagreement command for examining proposals through questions, evidence, edge cases, risks, and alternative approaches. It provides several levels of challenge, from gentle refinement to stronger opposition.

In plain words
What is it for?
Use it to challenge assumptions, test boundary cases, refine implementation details, assess risks, request supporting evidence, and compare alternative solutions.
Why use it?
It helps find weaknesses in a plan before implementation and makes the reasoning behind a decision easier to inspect. It turns disagreement into a repeatable review step.

Command

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 commands/dotclaude/marketplace/constructive_dissent
Clone the repo
git clone --depth 1 https://github.com/dotclaude/marketplace

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 constructive_dissent

README.md
[![agentmods](https://agentmods.dev/badge/commands/dotclaude/marketplace/constructive_dissent.svg)](https://agentmods.dev/commands/dotclaude/marketplace/constructive_dissent)
Your own site
<a href="https://agentmods.dev/commands/dotclaude/marketplace/constructive_dissent"><img src="https://agentmods.dev/badge/commands/dotclaude/marketplace/constructive_dissent.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,916 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 $0.00007 $0.02916
Opus 5 $0.00003 $0.01458
Sonnet 5 $0.00001 $0.00583
Haiku 4.5 $0.00001 $0.00292

Measured 3d ago against content hash c5da2eed49ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

constructive_dissent 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.

plugins/cognitive-orchestration/commands/constructive_dissent.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Constructive Disagreement Engine

Systematically challenge proposals through structured dissent protocols that strengthen solutions by exposing weaknesses, testing assumptions, and generating superior alternatives. Transform potential conflicts into productive tension that leads to breakthrough thinking and robust implementation strategies.

Dissent Intensity Framework

Gentle Level (Refinement-focused)

[Extended thinking: Question assumptions and suggest improvements without fundamental challenge to core approach. Focus on optimization and edge case consideration.]

Challenge Characteristics:

  • Assumption questioning with evidence request
  • Edge case identification with boundary testing
  • Implementation detail refinement with practical consideration
  • Risk mitigation with precautionary thinking
  • Alternative approach suggestion with comparative analysis

Dissent Approach:

  • "This approach has merit, but what if we considered..."
  • "I'm curious about how this would handle..."
  • "What assumptions are we making about..."
  • "Have we considered the implications of..."
  • "What evidence supports this direction over..."

Systematic Level (Methodology challenging)

[Extended thinking: Challenge underlying methods, frameworks, and approaches while maintaining respect for proposal intent. Focus on systematic weaknesses and alternative methodologies.]

Challenge Characteristics:

  • Methodology critique with alternative framework suggestion
  • Evidence evaluation with validation requirement
  • Stakeholder perspective integration with advocacy for unheard voices
  • Long-term consequence analysis with scenario planning
  • Resource allocation questioning with efficiency optimization

Dissent Approach:

  • "While the goal is sound, I question whether this methodology..."
  • "The evidence presented doesn't address..."
  • "From the perspective of [stakeholder], this approach might..."
  • "Long-term, this could lead to..."
  • "Have we considered more resource-efficient approaches like..."

Read the full file on GitHub · 271 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 · 271 lines · 7 tokens per session scan A c5da2eed49ba

Subscribe to this mod's changes

constructive_dissent is a command published in the GitHub repository dotclaude/marketplace (42 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 2,916 once invoked, about $0.0000 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.