ss-build

ss-build is a skill for Claude Code, Codex from bitjaru/styleseed. It costs 43 tokens per session (921 once invoked), scanned A, original, MIT.

A method for building screens with StyleSeed, a system of design rules for choosing layouts, styles, and visual details. It applies those rules to the project before writing interface code.

In plain words
What is it for?
Use it to build a screen from a brand recipe, page type, design profile, and other project constraints, then verify that the implementation follows them.
Why use it?
It reduces inconsistent design decisions and checks the result against the chosen rules. It also runs code and pixel-level checks before the screen is presented.

Skill for Claude CodeCodex

Part of the styleseed plugin — 24 skills 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/bitjaru/styleseed/ss-build
Any agent
npx skills add bitjaru/styleseed --skill ss-build
Clone the repo
git clone --depth 1 https://github.com/bitjaru/styleseed

Made for: Claude Code, Codex.

Or install styleseed, the plugin that ships this one along with the rest of its 24 skills.

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 ss-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/bitjaru/styleseed/ss-build.svg)](https://agentmods.dev/skills/bitjaru/styleseed/ss-build)
Your own site
<a href="https://agentmods.dev/skills/bitjaru/styleseed/ss-build"><img src="https://agentmods.dev/badge/skills/bitjaru/styleseed/ss-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 921 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 $0.00043 $0.00921
Opus 5 $0.00022 $0.00461
Sonnet 5 $0.00009 $0.00184
Haiku 4.5 $0.00004 $0.00092

Measured 4d ago against content hash 6da3ee935fc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ss-build 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.

engine/.claude/skills/ss-build/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build with the composed StyleSeed method

Registry-first artifact boundary

When .styleseed/project.json and .styleseed/artifacts/index.json exist, resolve the requested artifact ID first, then read only .styleseed/bundles/<artifact-id>.md and .styleseed/manifests/<artifact-id>.json. Never fall back to the global legacy bundle for a registry project. Legacy projects may use .styleseed/effective-rules.md only when no registry exists.

The build method is the product. Score and screenshots are auxiliary evidence, not the source of design judgment.

Step 1 — Establish the rule set before code

If STYLESEED.md does not exist, run /ss-setup and write it before UI code. If the user supplied a visual reference that the selected built-in grammar does not capture, run /ss-reference first. Never reduce an unfamiliar reference to a palette swap.

Then invoke /ss-resolve (Claude Code) or $ss-resolve (Codex), or run its bundled scripts/resolve-context.mjs --project-root . --from-lock STYLESEED.md --agent <agent>. Read .styleseed/effective-rules.md and preserve .styleseed/manifest.json as the provenance record. Do not load llms-full.txt after resolution succeeds.

Step 2 — Compose, do not improvise

The compiled bundle already composes the authority order: core invariants → selected grammar → surface adapter → domain/page → brand recipe → optional profile → bounded lock → craft baseline. Use the manifest selection and source hashes to detect drift. Open a full source document only when the bundle points to a genuine ambiguity; do not reassemble the handbook ad hoc.

Before code, state the effective rule set in one line, for example:

operations-console × SaaS × dashboard × enterprise-workbench × swiss × locked brand tokens

Resolve conflicts by authority. A profile or lock cannot waive task fitness, coherence, or accessibility.

Step 3 — Build with design judgment

  • Make the grammar's user job and primary decision visible in the first viewport.
  • Establish one focal point; avoid equal-weight template grids.
  • Use the grammar's composition, density, type, color, surface, imagery/data, action, state, responsive, and motion contracts.
  • Use the recipe's containment, geometry, control, collection, and navigation morphology. Set data-styleseed-recipe="<id>" on the artifact root when using bundled pattern components.
  • Use product-specific content and evidence. Never copy the StyleSeed demo or a reference screen.
  • Implement loading, empty, error, focus, reduced-motion, and responsive behavior where relevant.

Read the full file on GitHub · 84 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 · 84 lines · 43 tokens per session scan A 6da3ee935fc1

Subscribe to this mod's changes

ss-build is a skill published in the GitHub repository bitjaru/styleseed (939 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 921 once invoked, about $0.0002 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 2026-08-30.