design-debate

design-debate is a skill for Claude Code, Codex from dentiny/kon. It costs 35 tokens per session (1,907 once invoked), scanned A, original, MIT.

A structured argument between two agents that checks a software plan before coding starts. One agent challenges the plan and the other revises it.

In plain words
What is it for?
Use it after exploring a codebase and drafting a plan when a design needs stress-testing. It helps decide whether the proposed solution is correct and as simple as possible.
Why use it?
It exposes hidden assumptions and unnecessary complexity before they become code. It also makes uncertainty visible instead of filling gaps with guesses.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

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/dentiny/kon/design-debate
Any agent
npx skills add dentiny/kon --skill design-debate
Clone the repo
git clone --depth 1 https://github.com/dentiny/kon

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 design-debate

README.md
[![agentmods](https://agentmods.dev/badge/skills/dentiny/kon/design-debate.svg)](https://agentmods.dev/skills/dentiny/kon/design-debate)
Your own site
<a href="https://agentmods.dev/skills/dentiny/kon/design-debate"><img src="https://agentmods.dev/badge/skills/dentiny/kon/design-debate.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,907 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 $0.00035 $0.01907
Opus 5 $0.00017 $0.00954
Sonnet 5 $0.00007 $0.00381
Haiku 4.5 $0.00003 $0.00191

Measured 5d ago against content hash 96c61d5bc91f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

design-debate 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/design-debate/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Debate

Consumer: /kon:design.

Core principles (always)

Follow skills/core-principles. Design debate exists to stress-test plans before code is written. Both challenger and reviser optimize for:

  1. First principles — don't hide the issue — restate the actual problem; does the plan solve that problem, or inherit assumptions / over-engineer?
  2. Simplest, most concise correct solution — most direct design Yui can execute without unnecessary layers.

Azusa must challenge complexity that lacks first-principles justification. Mugi must revise toward simpler designs when challenges are valid.

Do not invent risks or requirements to fill a debate round — if the plan is sound but you lack evidence, say so and ask. Follow skills/ask-dont-guess.

Design debate is real multi-agent argument, not the orchestrator summarizing both sides. Each round is a separate Task spawn with the agent file + this skill in context.

Roles

Phase Agent Mode Writes
Explore 🎸 Azusa default nothing (report only)
Plan v1 🍰 Mugi default .kon/plan-<session-id>.md
Challenge 🎸 Azusa challenge .kon/design-debate-<session-id>.md (challenges section)
Revise 🍰 Mugi revise .kon/plan-<session-id>.md + .kon/design-debate-<session-id>.md (responses)
Confirm user

Artifacts

.kon/design-debate-<session-id>.md

Created on first challenge round. Threaded log of argument:

# Design debate: <task name>

## Round 1 — Azusa challenges

### C1: <short title>
<why this is a gap, risk, or wrong assumption — cite files/lines>

### C2: ...

## Round 1 — Mugi responses

| ID | Verdict | Response | Plan change |
|----|---------|----------|-------------|
| C1 | accepted | ... | Step 2 split into 2a/2b |
| C2 | rejected | Plan already covers via Step 4 acceptance | none |

## Round 2 — Azusa challenges (only with --deep)
...

Read the full file on GitHub · 188 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 · 188 lines · 35 tokens per session scan A 96c61d5bc91f

Subscribe to this mod's changes

design-debate is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,907 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 2026-08-31.

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens