consensus

consensus is a skill for Claude Code from supportersimulator/3-surgeons. It costs 16 tokens per session (1,066 once invoked), scanned A, original, MIT.

A quick vote from several surgeon agents that checks a claim or assumption and reports how confident they are. It is meant for simple decisions, not detailed architectural or risk reviews.

In plain words
What is it for?
Use it to validate claims, check assumptions, perform quick sanity checks, verify compatibility, or settle a small technical disagreement.
Why use it?
It adds a fast second check before relying on an uncertain technical statement or choosing between plausible options.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the 3-surgeons plugin — 23 skills, 7 commands, 1 agent, 3 hooks, 1 MCP server shipped together

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 skills/supportersimulator/3-surgeons/consensus
Any agent
npx skills add supportersimulator/3-surgeons --skill consensus
Clone the repo
git clone --depth 1 https://github.com/supportersimulator/3-surgeons

Made for: Claude Code.

Or install 3-surgeons, the plugin that ships this one along with the rest of its 23 skills, 7 commands, 1 agent, 3 hooks, 1 MCP server.

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 consensus

README.md
[![agentmods](https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/consensus.svg)](https://agentmods.dev/skills/supportersimulator/3-surgeons/consensus)
Your own site
<a href="https://agentmods.dev/skills/supportersimulator/3-surgeons/consensus"><img src="https://agentmods.dev/badge/skills/supportersimulator/3-surgeons/consensus.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 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 5.1 $0.00016 $0.01066
Opus 5 $0.00008 $0.00533
Sonnet 5 $0.00003 $0.00213
Haiku 4.5 $0.00002 $0.00107

Measured 5d ago against content hash 49267d5642eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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.

skills/consensus/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consensus

When to Use

Consensus is the lightweight decision tool -- a quick confidence-weighted vote rather than a full cross-examination. Use it when:

  • Validating a claim -- "Is this approach safe?" "Does this pattern follow best practices?"
  • Checking assumptions -- before building on an assumption, verify it with both models
  • Pre-commit verification -- "Will this change break backwards compatibility?"
  • Resolving simple disagreements -- when you have two plausible options and need a tiebreaker
  • Quick sanity checks -- "Is this the right data structure for this use case?"

Do NOT use for: complex architectural decisions (use cross-examination), health checks (use probe), or risk assessment (use sentinel).

How to Invoke

CLI

3s consensus "Redis LPUSH is O(1) for single elements"

MCP Tool

consensus(claim="Redis LPUSH is O(1) for single elements")

How It Works

Each surgeon receives the claim and responds with a JSON assessment:

{
  "confidence": 0.85,
  "assessment": "agree",
  "reasoning": "Redis LPUSH is documented as O(1) per element..."
}

The system then calculates a weighted consensus score:

weighted_score = sum(confidence_i * assessment_value_i) / sum(confidence_i)

Where assessment values are: agree = +1.0, uncertain = 0.0, disagree = -1.0.

Interpreting the Weighted Score

Score Range Meaning Action
+0.7 to +1.0 Strong agreement Proceed with confidence. Both surgeons agree the claim is valid.
+0.3 to +0.7 Moderate agreement Proceed but verify. One surgeon is less confident or uncertain.
-0.3 to +0.3 Uncertain / Split Do not proceed blindly. Consider escalating to full cross-examination.
-0.7 to -0.3 Moderate disagreement The claim is likely wrong or oversimplified. Investigate further.
-1.0 to -0.7 Strong disagreement The claim is rejected by both surgeons. Re-examine your assumption.

Read the full file on GitHub · 113 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. 5d ago First seen · 113 lines · 16 tokens per session scan A 49267d5642eb

Subscribe to this mod's changes

consensus is a skill published in the GitHub repository supportersimulator/3-surgeons (2 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 1,066 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.

Related

Other skills, from other repositories

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

zhayujie/CowAgent · 41 tokens

deepcode-self-refer

Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such…

lessweb/deepcode-cli · 86 tokens

image-generator

Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

lessweb/deepcode-cli · 62 tokens

weibo-poster

微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.

dongsheng123132/u-claw · 32 tokens

xiaohongshu-writer

小红书笔记写作助手 - 标题优化、emoji策略、话题标签、封面文案、笔记结构.

dongsheng123132/u-claw · 35 tokens