multi-agent-voting

multi-agent-voting is a skill for Claude Code from marcusgoll/Spec-Flow. It costs 0 tokens per session (1,589 once invoked), scanned A, original, MIT.

A decision process that asks multiple agents to vote on important technical choices and requires a clear lead before selecting an answer.

In plain words
What is it for?
It helps reach agreement on code reviews, breaking changes, and specification validation when voting is enabled.
Why use it?
It reduces the chance that one agent makes an incorrect choice on high-stakes changes, reviews, or specifications.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps reach agreement on code reviews, breaking changes, and specification validation…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcusgoll/spec-flow/multi-agent-voting
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.

Any agent
npx skills add marcusgoll/Spec-Flow --skill multi-agent-voting
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

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 multi-agent-voting

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusgoll/spec-flow/multi-agent-voting.svg)](https://agentmods.dev/skills/marcusgoll/spec-flow/multi-agent-voting)
Your own site
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/multi-agent-voting"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/multi-agent-voting.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,589 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 $0.00000 $0.01589
Opus 5 $0.00000 $0.00794
Sonnet 5 $0.00000 $0.00318
Haiku 4.5 $0.00000 $0.00159

Measured 3d ago against content hash 104018179dce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

multi-agent-voting 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.

The scan reads SKILL.md. This mod also ships 2 executable files (vote-aggregator.py, voting-engine.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/multi-agent-voting/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Voting Skill

Execute multi-agent voting for critical decisions using MAKER-style first-to-ahead-by-k error correction.

When to Use

Use this skill when:

  • Making critical decisions that benefit from consensus (code review, breaking changes, spec validation)
  • Voting is enabled in .spec-flow/config/voting.yaml for the operation type
  • High-stakes decisions where single-agent errors are unacceptable

Theoretical Foundation

Based on MAKER paper (arXiv:2511.09030):

  • First-to-ahead-by-k voting: Candidate must be k votes ahead to win
  • Formula: p_correct = p^k / (p^k + (1-p)^k)
  • Scaling: Cost grows log-linearly O(s ln s) with decomposition

With k=2 and individual agent accuracy of 70%:

  • Single agent: 70% accuracy
  • 3 agents with k=2: ~84% accuracy
  • 5 agents with k=3: ~91% accuracy

Prerequisites

Workflow

Read the full file on GitHub · 234 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 234 lines · 0 tokens per session scan A 104018179dce

Subscribe to this mod's changes

multi-agent-voting is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,589 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 2026-09-03.