design

design is a skill for Claude Code, Codex from lantisprime/claude-sdlc. It costs 109 tokens per session (998 once invoked), scanned A, original, MIT.

A design-phase tool that turns approved requirements into technical plans for building and testing software. Its outputs cover application, data, platform, infrastructure, security, testing, API and data contracts, and delivery pipelines.

In plain words
What is it for?
Use it after the analysis phase to create or update architecture files, technical specifications, test cases linked to requirement IDs, and a DevOps pipeline design.
Why use it?
It gives the build and test work shared documents to follow, instead of leaving architecture and test decisions scattered or implicit. It also checks existing design documents before changing them.

Skill for Claude CodeCodex

Part of the sdlc-plugin plugin — 19 skills, 16 commands, 10 agents, 4 hooks shipped together

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/lantisprime/claude-sdlc/design
Any agent
npx skills add lantisprime/claude-sdlc --skill design
Clone the repo
git clone --depth 1 https://github.com/lantisprime/claude-sdlc

Made for: Claude Code, Codex.

Or install sdlc-plugin, the plugin that ships this one along with the rest of its 19 skills, 16 commands, 10 agents, 4 hooks.

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/skills/lantisprime/claude-sdlc/design.svg)](https://agentmods.dev/skills/lantisprime/claude-sdlc/design)
Your own site
<a href="https://agentmods.dev/skills/lantisprime/claude-sdlc/design"><img src="https://agentmods.dev/badge/skills/lantisprime/claude-sdlc/design.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 998 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 $0.00109 $0.00998
Opus 5 $0.00055 $0.00499
Sonnet 5 $0.00022 $0.00200
Haiku 4.5 $0.00011 $0.00100

Measured 4d ago against content hash 59a346b8b065, 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 4d 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.

skills/design/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design (Phase 3)

Produce the artifacts Build will reference and Test will execute against.

Prerequisite

.claude/sdlc/gates/analyze-<task-slug>.md must exist and be signed.

Artifacts produced (or updated)

All live under .claude/sdlc/architecture/ with a manifest.json index:

  1. Application architecture — components, integrations, data flow, NFRs (performance, availability, scalability)
  2. Data architecture — entities, schema changes, flows, retention, classification
  3. Platform architecture — runtimes, orchestration, environments
  4. Infrastructure architecture — compute, network, storage, identity
  5. Security architecture — threat model, controls, secrets handling, authn/authz
  6. Test architecture — pyramid shape, test types, tooling, environments, test-data strategy
  7. Technical specifications — API contracts, data contracts, module responsibilities (under .claude/sdlc/tech-specs/)
  8. Test cases — one or more per requirement, each tied to REQ IDs (under .claude/sdlc/test-cases/)
  9. DevOps pipeline design — stages, gates, environments, promotion rules

Rule: validate before rewriting

If architecture artifacts already exist:

  • Read them.
  • Produce a validation report comparing existing architecture against the current requirements set.
  • Surface deltas (new NFRs, new entities, new integrations, new controls) for human decision.
  • Only after the human agrees, update the affected files. Never wholesale-regenerate a working architecture.

Test-case rule

Each requirement gets at least one test case. Each test case references:

  • The REQ IDs it covers
  • The test type (unit / integration / e2e / NFR)
  • Preconditions, steps, expected outcome
  • Data needs

Use templates/test-case.md.

Tech spec rule

For each in-scope module or service, produce or update a spec under .claude/sdlc/tech-specs/. Specs are the contract Build validates its code against — API shape, inputs/outputs, error modes, side effects, NFR commitments.

Read the full file on GitHub · 96 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. 4d ago First seen · 96 lines · 109 tokens per session scan A 59a346b8b065

Subscribe to this mod's changes

design is a skill published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It adds 109 tokens to every session and 998 once invoked, about $0.0005 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.