design

design is a command for Claude Code from rafadorado/qrspiv. It costs 14 tokens per session (2,067 once invoked), scanned A, original, MIT.

A guided design discussion phase for a software task, held before detailed planning and coding. It records the task, checks assumptions, and examines existing code patterns and implementation details.

In plain words
What is it for?
It helps research the relevant codebase, identify files and components involved, document how they currently work, and agree on a design for the requested feature.
Why use it?
It helps find unclear requirements, unsuitable design choices, and misunderstandings before they lead to a long implementation plan or large code change.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the qrspiv plugin — 7 commands shipped together

Good fit It helps research the relevant codebase, identify files and components involved, document how they currently work, and agree on a design for the requested feature.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rafadorado/qrspiv/design
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.

Clone the repo
git clone --depth 1 https://github.com/rafadorado/qrspiv

Made for: Claude Code.

Or install qrspiv, the plugin that ships this one along with the rest of its 7 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/rafadorado/qrspiv/design/github.svg)](https://agentmods.dev/commands/rafadorado/qrspiv/design)
Your own site
<a href="https://agentmods.dev/commands/rafadorado/qrspiv/design"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design

Your own site · 80×15
<a href="https://agentmods.dev/commands/rafadorado/qrspiv/design"><img src="https://agentmods.dev/badge/commands/rafadorado/qrspiv/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,067 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 $0.00014 $0.02067
Opus 5 $0.00007 $0.01033
Sonnet 5 $0.00003 $0.00413
Haiku 4.5 $0.00001 $0.00207

Measured 9d ago against content hash d0a7abd7a95d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design 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 9d 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.

commands/design.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Discussion (S Phase)

Plans are 1000+ lines and map roughly 1:1 to code. Reviewing a plan is nearly as much work as reviewing the code. This design discussion surfaces wrong assumptions, bad pattern choices, and misunderstood requirements in a ~200-line document — before the agent writes 2000 lines of code.

If individual file paths were provided, read them all fully.

If no parameters provided, respond with:

"I'll help create a design discussion for your task. Point me to the thoughts folder for your work item (e.g., thoughts/001-auth-endpoint/), or provide your task description and research findings."

Then wait for the user's input.

Then spawn focused research agents to fill gaps:

  • Use codebase-pattern-finder to locate the specific patterns referenced in the research. Instruct it to document what exists — not evaluate or recommend.
  • Use codebase-analyzer on any component that will be directly modified. Instruct it to explain the implementation — not suggest design choices.

Wait for agents to complete.

If gaps exist, spawn additional research or ask the user before continuing.

Design Discussion: [Feature/Task Name]

Task Summary (5 lines max)

[What we're building and why, from the task definition]

Current State (15 lines max)

[How the relevant parts of the system work today. Be specific — file paths, key functions, data flows. This comes from the research.]

Desired End State (15 lines max)

[What the system should look like after implementation. Be concrete enough that someone could verify it.]

Patterns to Follow

[Existing patterns in the codebase that this work should mirror. Include file:line references.]

  • Pattern: [name] — found in path/to/file.ext:L42 [Brief description of the pattern]

Patterns to AVOID

[Bad patterns, deprecated approaches, or legacy code that should NOT be followed.]

  • Anti-pattern: [name] — exists in path/to/old_file.ext:L99 [Why this should not be used]

Design Decisions

Resolved by Architecture

[ONLY decisions that are logically forced by the task definition, existing architecture, or codebase constraints. These are not opinions — they are facts.]

  1. [Decision]: [Choice] — forced by [architectural constraint or existing pattern]

Open Questions for Human

[Everything else. All trade-offs, preference-based choices, and design directions go here. The human decides.]

  1. [Question]: [Context for why this matters]
    • Option A: [description + tradeoff]
    • Option B: [description + tradeoff] Present facts about each option. Do NOT express a preference.

Key Risks & Edge Cases (10 lines max)

[Things that could go wrong or need special attention]

  • [Risk]: [mitigation approach]

Out of Scope

[What we're explicitly NOT doing]

</template>

<critical>
The "Resolved by Architecture" section must ONLY contain decisions forced by constraints — not the agent's preferences. If there's any room for choice, it belongs in "Open Questions for Human."

Read the full file on GitHub · 222 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. 9d ago First seen · 222 lines · 14 tokens per session scan A d0a7abd7a95d

Subscribe to this mod's changes

design is a command published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 2,067 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.