spec-to-design

spec-to-design is a command for Claude Code from Zts0hg/codexspec. It costs 15 tokens per session (1,311 once invoked), scanned A, original, MIT.

A tool that turns a confirmed specification, a written description of what a system must do, into a traceable design document. It follows the project’s language settings when writing the document.

In plain words
What is it for?
Use it after confirming a specification to document the system’s architecture, components, interfaces, and key design choices.
Why use it?
It connects agreed requirements to the system structure and design decisions, making it easier to see how the design fulfils the specification.

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/zts0hg/codexspec/spec-to-design
Clone the repo
git clone --depth 1 https://github.com/Zts0hg/codexspec

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 spec-to-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/zts0hg/codexspec/spec-to-design.svg)](https://agentmods.dev/commands/zts0hg/codexspec/spec-to-design)
Your own site
<a href="https://agentmods.dev/commands/zts0hg/codexspec/spec-to-design"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/spec-to-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,311 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 $0.00015 $0.01311
Opus 5 $0.00008 $0.00656
Sonnet 5 $0.00003 $0.00262
Haiku 4.5 $0.00002 $0.00131

Measured yesterday against content hash 63d89107dee6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-to-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 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.

.claude/commands/codexspec/spec-to-design.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification to Design Converter

Language Preference

Read .codexspec/config.yml. Two independent language controls apply (each falls back to language.output, then English):

  • Interaction language (language.interaction): language for all conversation with the user — questions, explanations, status messages, and codexspec CLI terminal output.
  • Document language (language.document): language for generated artifact files (requirements/spec/plan/tasks).

Converse in the interaction language and author artifacts in the document language. Apply the project's translation standard to both: translate by meaning (not word-for-word), keep English for terms with no good native equivalent, and write as if originally in that language.

User Input

$ARGUMENTS

Role

Act as a constrained system designer. Define what the system is — architecture, components, interfaces, and key design decisions — that realizes the specification, while preserving confirmed user intent. Do not plan how to build it in phases; that belongs to the downstream plan stage.

Feature Resolution

Use an explicit path first, then the current branch. If neither uniquely identifies a feature, ask the user to select one. Never silently select the latest feature.

Read:

  • requirements.md
  • spec.md
  • .codexspec/memory/constitution.md when present
  • Relevant repository files needed to verify existing patterns and constraints

Legacy compatibility: if requirements.md is absent, treat spec.md as the temporary highest authority and disclose that original-discussion fidelity cannot be checked.

Authority and Stop Conditions

Authority order:

  1. Confirmed requirements.md
  2. spec.md
  3. Constitution and verified repository facts
  4. Design-level technical decisions
  5. General best practices

Before designing, verify that spec.md covers the confirmed requirements. Stop if it omits, contradicts, or silently expands them.

Stop and request a user decision when:

Read the full file on GitHub · 122 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. yesterday Changed · +7 lines · +5 tokens per session 63d89107dee6
  2. 5d ago First seen · 115 lines · 10 tokens per session scan A a079a007182f

Subscribe to this mod's changes

spec-to-design is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 1,311 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.