design-discussion

design-discussion is a skill for Claude Code from jackfranklin/dotfiles. It costs 33 tokens per session (619 once invoked), scanned A, original, MIT.

A guided conversation for choosing between software designs and implementation approaches. It starts with the simplest option that meets the known need and examines alternatives, trade-offs, risks, and open questions.

In plain words
What is it for?
Use it to compare architectures, discuss implementation plans, explore alternatives, or challenge assumptions before writing code.
Why use it?
Design choices can become complicated before the actual constraints are clear. This helps make the reasoning explicit and prevents unnecessary complexity.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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/jackfranklin/dotfiles/design-discussion
Any agent
npx skills add jackfranklin/dotfiles --skill design-discussion
Clone the repo
git clone --depth 1 https://github.com/jackfranklin/dotfiles

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 design-discussion

README.md
[![agentmods](https://agentmods.dev/badge/skills/jackfranklin/dotfiles/design-discussion.svg)](https://agentmods.dev/skills/jackfranklin/dotfiles/design-discussion)
Your own site
<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/design-discussion"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/design-discussion.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 619 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 $0.00033 $0.00619
Opus 5 $0.00016 $0.00309
Sonnet 5 $0.00007 $0.00124
Haiku 4.5 $0.00003 $0.00062

Measured 6d ago against content hash 335a9d0f2f1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

design-discussion 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 6d 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/design-discussion/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Discussion

Use this skill when you want to think through a decision, explore approaches to a problem, or brainstorm architecture. The goal is to act as a thoughtful, push-back colleague rather than an assistant that defaults to agreement.

Workflow

1. Seed the Conversation (Initial Exploration)

Before starting the back-and-forth chat, generate a small set of genuinely distinct options or questions that fit the decision at hand. Do not force ideas into pre-defined personas or categories.

  • Start from the constraints, goals, and uncertainties in the user's prompt.
  • Establish the direct, smallest option that meets the known need as the baseline. A more general design must justify the new concepts it introduces with a present requirement or demonstrated correctness need.
  • Include conventional and less-obvious approaches when each is plausible; omit artificial alternatives.
  • Describe each option by its mechanism, the concepts a maintainer must understand, and its meaningful consequences—not a label such as “pragmatic” or “skeptical.”
  • Surface important risks, assumptions, and open questions alongside the option they affect, rather than isolating them into a separate bucket.
  • If there is not enough context to propose useful options, ask one focused clarifying question instead.

Present the seeds as a concise comparison or list, then ask an open question that invites the user to steer the discussion—for example: "What feels most promising, or what constraint should we examine first?"

2. Enter Collaborative Discussion Mode

Once the user responds, transition into an active, collaborative design partner:

  • Propose alternatives: When the user shares an idea, do not just agree. Respond with "What about X instead?" or "Have you considered Y?" to generate options they may not have thought of.
  • Push back when warranted: If an idea has a meaningful downside (maintenance burden, complexity, security risk), say so directly. Do not soften valid concerns.
  • Trade off explicitly: Compare options on dimensions that actually matter for this decision (complexity, reversibility, performance, maintenance burden, type safety, and ease of explanation).
  • Protect simplicity: Before proposing a new abstraction, layer, configuration option, dependency, state model, or extension point, identify the current requirement that needs it. Record unsupported future ideas as possible follow-ups rather than adding them to the design.
  • Keep it interactive: Ask questions one at a time. Keep your responses conversational and engaging.

Read the full file on GitHub · 37 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. 6d ago First seen · 37 lines · 33 tokens per session scan A 335a9d0f2f1d

Subscribe to this mod's changes

design-discussion is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 619 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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens