What is styleseed AGENTS.md?

A repository guide for coding agents working on StyleSeed, an AI design-method engine that generates design outputs from project rules and references. It explains which instructions and generated files are authoritative.

Use it before changing StyleSeed’s engine, skills, components, skins, demos, or generated files. It also guides verification, pull requests, and releases.

It reduces mistakes caused by changing the wrong files or missing project-specific rules. It also helps keep source instructions, generated demos, and release work aligned.

styleseed AGENTS.md — Instructions file by bitjaru

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 instructions/bitjaru/styleseed/agents-md

Clone the repo

git clone --depth 1 https://github.com/bitjaru/styleseed

Made for: Codex, OpenCode.

Per session 540 This file is loaded in full into every session.

When invoked 540 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00540	$0.00540
Opus 5	$0.00270	$0.00270
Sonnet 5	$0.00108	$0.00108
Haiku 4.5	$0.00054	$0.00054

Measured 2d ago against content hash eecd03f5affe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

styleseed AGENTS.md 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.

AGENTS.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StyleSeed repository guide

StyleSeed is an AI design-method engine for coding agents. It combines fixed judgment, job-specific output grammars, surface adapters, and project-local reference grammars. Keep the rules, skills, components, skins, and generated demo artifacts in sync.

Before changing the engine

Read engine/AGENTS.md for the cross-agent design rules.
Read the relevant nested guide before editing its subtree. In particular, demo-pricing/AGENTS.md applies to the Next.js demo.
Read engine/PRODUCT-PRINCIPLES.md, engine/RULESETS.md, engine/ADAPTERS.md, engine/BRAND-RECIPES.md, engine/PALETTE-RECIPES.md, and engine/ARCHITECTURE.md before changing product behavior.
Treat engine/.claude/skills/ as the canonical source for all 23 StyleSeed skills. .agents/skills is a repository-scoped Codex symlink to that same directory. Root skills/ is the generated physical mirror used by Codex plugin archives; never edit it directly.
Claude Code invokes a skill as /ss-setup, /ss-build, and so on. Codex invokes it as $ss-setup, $ss-build, or from its Skills picker.

Generated files

demo-pricing/scripts/build-llms.mjs regenerates the public agent index, registry, context catalog, skin bundle, engine mirrors, plugin skill mirror, and llms.txt/llms-full.txt. Edit the source in engine/ or skins/, then run the generator; do not hand-edit generated copies as the source of truth.

Verification

Every engine change: run node scripts/validate-palettes.mjs, node scripts/validate-engine.mjs, and git diff --check.
Engine, skin, component, registry, or demo changes: run npm run build from demo-pricing/, then run git diff --check from the repository root.
The demo build fetches Google Fonts and may require network access.
Do not claim a visual pass without rendering and inspecting the affected UI.

Pull requests and releases

Keep unrelated design-canon changes, tooling changes, and compatibility work in separate commits or pull requests.
Do not change engine/VERSION, the changelog, or publish a release unless the maintainer explicitly includes release work in the task.

Read the full file on GitHub · 44 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.

2d ago First seen · 44 lines · 540 tokens per session scan A eecd03f5affe

Subscribe to this mod's changes

styleseed AGENTS.md is an instructions file published in the GitHub repository bitjaru/styleseed (928 stars, last pushed 7d ago), licensed MIT. It adds 540 tokens to every session, about $0.0027 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.

Design and UX ai-coding claude-code design-system design-tokens shadcn-ui

Design-Learn CLAUDE.md

Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.

GalaxyXieyu/Design-Learn · 1,900 tokens

oh-my-design CLAUDE.md

Instructions for kwakseongjae/oh-my-design, a project described as: Give your AI coding agent a design system. One command installs 400+ quality-graded company DESIGN.md references + skills into Claude Code, Codex, Cursor, and OpenCode. Free, MIT, zero AI calls.

kwakseongjae/oh-my-design · 152 tokens

styleseed AGENTS.md