design

A design interview and documentation command for deciding a project’s architecture, data model, platform, and behavior. Architecture describes how parts of a system fit together.

In plain words
What is it for?
Designing components and boundaries, database schemas, runtime behavior, synchronization, build-versus-buy choices, tradeoffs, and a behavioral specification.
Why use it?
It helps make important technical decisions explicit and keeps future changes localized rather than spreading through the whole project.

Command for Claude Code

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 commands/robconery/cassini-workshop/design
Clone the repo
git clone --depth 1 https://github.com/robconery/cassini-workshop

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 723 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 $0.00021 $0.00723
Opus 5 $0.00010 $0.00362
Sonnet 5 $0.00004 $0.00145
Haiku 4.5 $0.00002 $0.00072

Measured 2d ago against content hash 6ea78fe896e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

  • design — 100% identical, 0 lines differ
  • design — 100% identical, 0 lines differ
.claude/commands/design.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

design

🎯 Design for change. Every architectural decision here is judged by one question: when this changes, how big is the diff? Pick the boundaries, seams, and data shapes that make the next change small and local.

Decide how to build what /explore defined. This is a solution-space interview. Output: an architecture, a data model, and a behavioral spec.

Scope

  • IN: components & boundaries, data model, database (schema and platform), runtime, sync vs async, build-vs-buy, key tradeoffs, behavioral requirements.
  • OUT: the problem/why (that's /explore — read it, don't redo it), task breakdown (/plan), prose docs/README (/document).

Preflight

  1. Read docs/PROJECT.md (the brief — design must serve it), plus docs/ARCHITECTURE.md, docs/SPEC.md, CLAUDE.md, docs/MEMORY.md. Summarize current state in 1–2 lines. Re-entrant: refine, don't restart.
  2. If PROJECT.md still has open scope questions, surface them — designing on an undefined problem is wasted work; offer to bounce back to /explore.

Skills

Pull in the relevant skill rather than improvising:

  • DB schema → postgres-dba (or sqlite-dev if local/Bun + SQLite).
  • Module/class boundaries → solid-principles, design-principles.
  • Pattern choice → gof-patterns. TS conventions → typescript-best-practices.

Interview

Up to ~10 questions, adaptive, batched (4 at a time). Bank:

  1. Data model — core entities and relationships?
  2. Database platform, and why (durability, scale, ops)?
  3. Runtime / language / framework — and any locked constraints?
  4. Major components and their boundaries?
  5. Sync or async? Where are the seams?
  6. External services / APIs — build or buy?
  7. Auth & trust boundaries, if any?
  8. Hardest technical risk, and the fallback?
  9. What are we explicitly not building for now (YAGNI)?
  10. Non-functionals that bite: scale, latency, offline, cost ceiling?

Produce

  • docs/ARCHITECTURE.md (owned): components, data flow, the data model, database platform + schema, key decisions with their rationale and the alternative rejected.
  • docs/SPEC.md (owned): behavioral requirements in prose — what the system must do, observably. This is what /plan slices into stories; keep it testable, not vague.
  • docs/PROJECT.md: update the decisions log only (don't rewrite it).
  • docs/MEMORY.md: append dated entries for each architectural decision — the choice, the why, the rejected alternative.

Read the full file on GitHub · 69 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. 2d ago First seen · 69 lines · 21 tokens per session scan A 6ea78fe896e7

Subscribe to this mod's changes

design is a command published in the GitHub repository robconery/cassini-workshop (1 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 723 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.