design-feature

A planning command for designing a software feature before writing its code, using the project's existing requirements and past decisions.

In plain words
What is it for?
Compare at least two ways to build a feature, recommend one, record the decision, and update the project specification when needed.
Why use it?
It makes important design choices explicit and helps avoid coding against unclear or conflicting requirements.

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/erniker/understudy/design-feature
Clone the repo
git clone --depth 1 https://github.com/erniker/understudy

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 162 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 $0.00011 $0.00162
Opus 5 $0.00005 $0.00081
Sonnet 5 $0.00002 $0.00032
Haiku 4.5 $0.00001 $0.00016

Measured yesterday against content hash d3cd61567780, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-feature 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 yesterday.

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.

templates/.claude/commands/design-feature.md · 19 lines

What it actually says

I need to design a new feature for this project. Act as the Solutions Architect.

Process to follow:

  1. Read docs/spec.md for project context
  2. Read docs/decisions.md for previous decisions
  3. Ask me about the feature I need (requirements, users, constraints)
  4. Propose at least 2 architectural alternatives with pros/cons
  5. Recommend one option with justification
  6. Document the decision as a new ADR in docs/decisions.md
  7. If applicable, update docs/spec.md with the new requirements
  8. Produce Mermaid diagrams if they help explain the design

Do not write code yet — design first, implementation afterwards.

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. yesterday First seen · 19 lines · 11 tokens per session scan A d3cd61567780

Subscribe to this mod's changes

design-feature is a command published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 162 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.