consensus

A command that examines a question from supportive, opposing, and neutral viewpoints before reaching a shared conclusion. It uses several parallel analyses and includes initial context gathering.

In plain words
What is it for?
Use it to evaluate a technical proposal, design choice, or other question where competing considerations matter. It can inspect relevant files and documentation and search for current practices when appropriate.
Why use it?
Looking at one proposal from only one angle can hide risks or trade-offs. Comparing different viewpoints helps expose arguments for and against a decision.

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/krmcbride/claude-plugins/consensus
Clone the repo
git clone --depth 1 https://github.com/krmcbride/claude-plugins
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,223 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 $0.00020 $0.01223
Opus 5 $0.00010 $0.00611
Sonnet 5 $0.00004 $0.00245
Haiku 4.5 $0.00002 $0.00122

Measured 2d ago against content hash 294733b62e90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consensus 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.

essentials/commands/consensus.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze this question from multiple perspectives to provide comprehensive consensus-based guidance.

Question to Analyze:

$ARGUMENTS

Consensus Workflow

Step 1: Gather Initial Context

Before launching perspective agents:

  • Use Read, Grep, Glob, or WebSearch to understand the question's domain
  • Identify relevant files, code patterns, existing implementations, or documentation
  • Search for current best practices, benchmarks, or documented pitfalls if appropriate
  • Prepare 3-5 sentences of objective context about the topic

Step 2: Launch Three Parallel Analyses

Launch 3 parallel Sonnet agents with different analytical stances. Provide each with:

  • The original question
  • The gathered context from step 1
  • Any relevant file paths or code snippets discovered

FOR Agent Instructions (Advocacy)

You are an advocate analyzing through a supportive lens. Your stance is FOR - seek reasons to support this idea.

Core principles:

  • Find at least ONE COMPELLING reason to be optimistic
  • Acknowledge genuine concerns but frame constructively
  • Refuse support if the idea is fundamentally harmful to users, project, or stakeholders
  • Override your supportive stance when ideas violate security, privacy, or ethical standards
  • Your stance influences HOW you present findings, not WHETHER you acknowledge truths

Research before analysis:

  • Use Read/Grep to find supporting evidence in codebase
  • WebSearch for best practices, success stories, or industry trends
  • Ground arguments in evidence - cite specific code locations (file:line)
  • State when evidence is inconclusive

Framework - analyze:

  1. Potential benefits and value proposition
  2. How challenges could be overcome
  3. Why this might be the right approach
  4. Supportive framing of trade-offs

Output format (850 tokens max):

  1. Position - One sentence stating your stance
  2. Primary Argument - Strongest point with evidence
  3. Secondary Considerations - 2-3 additional points in favor
  4. Acknowledgments - What concerns have merit
  5. Bottom Line - Conclusion in one sentence

Read the full file on GitHub · 192 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 · 192 lines · 20 tokens per session scan A 294733b62e90

Subscribe to this mod's changes

consensus is a command published in the GitHub repository krmcbride/claude-plugins (3 stars, last pushed 8mo ago), licensed MIT. It adds 20 tokens to every session and 1,223 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 2026-08-31.