decide

decide is a skill for Claude Code, Codex from dirien/yet-another-agent-harness. It costs 48 tokens per session (1,420 once invoked), scanned A, original, MIT.

A structured three-agent discussion process for choosing between at least two options. Two advocates argue opposing positions, and a moderator tests the reasoning and writes the final consensus.

In plain words
What is it for?
Use it to compare alternatives, evaluate tradeoffs, and reach a documented decision; factual questions and single-option requests should be answered directly.
Why use it?
It exposes risks and overlooked arguments before a strategic or high-stakes decision is made.

Skill for Claude CodeCodex

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/dirien/yet-another-agent-harness/decide
Any agent
npx skills add dirien/yet-another-agent-harness --skill decide
Clone the repo
git clone --depth 1 https://github.com/dirien/yet-another-agent-harness

Made for: Claude Code, Codex.

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 decide

README.md
[![agentmods](https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/decide.svg)](https://agentmods.dev/skills/dirien/yet-another-agent-harness/decide)
Your own site
<a href="https://agentmods.dev/skills/dirien/yet-another-agent-harness/decide"><img src="https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/decide.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,420 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 $0.00048 $0.01420
Opus 5 $0.00024 $0.00710
Sonnet 5 $0.00010 $0.00284
Haiku 4.5 $0.00005 $0.00142

Measured 5d ago against content hash 649beecc3a9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decide 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.

.claude/skills/decide/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Consensus Protocol

Run a structured three-agent debate to reach consensus on a strategic decision. Two advocates steelman opposing positions while a moderator asks hard questions, identifies risks, and synthesizes the binding consensus.

Why this works: adversarial structure surfaces arguments brainstorming misses. Evidence-grounded research prevents epistemic closure. Forced concessions in Round 2 prevent entrenchment. The moderator writes the binding consensus after hearing both sides.

Pre-flight validation

Before running the debate, verify the input contains a genuine decision with at least two distinguishable options or courses of action.

If the input is a factual question, explanation request, or single-option statement, respond directly instead: "This protocol works best when choosing between alternatives. Could you rephrase with the options you're weighing, or ask me directly?"

When in doubt, proceed — err on the side of running the debate.

Phase 0: Research and frame the decision

Step 0.1: Gather context

Read project documentation and context files to understand the decision space. Common sources include README, architecture docs, product docs, recent git history, and any files the user referenced.

Step 0.2: Identify the two positions

From the decision topic, formulate two clear, opposing positions:

  • Position A: one side of the decision
  • Position B: the opposing side

If the topic naturally implies two sides (e.g., "gRPC vs REST"), use those directly. If the topic is open-ended (e.g., "pricing strategy"), research the space and formulate the two strongest opposing approaches.

Step 0.3: Identify constraints

Extract hard constraints from the user's message or project docs: budget limits, timeline requirements, team size, technical constraints, business requirements, non-negotiable values.

Read the full file on GitHub · 175 lines

Files

What ships with it

1 file 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. 5d ago First seen · 175 lines · 48 tokens per session scan A 649beecc3a9d

Subscribe to this mod's changes

decide is a skill published in the GitHub repository dirien/yet-another-agent-harness (20 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,420 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens