styleseed

Skill · GitHub · ★ 992 · graded 2026-10-23Source linked

Open-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows for fixed design judgment, multiple grammars, semantic palettes, reference compilation, and evidence-verified UI. MIT.

No outside reports on file

Use styleseed only with design files you trust, never with sensitive data, and review all AI-generated code before deploying it.

Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Styleseed helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (bitjaru/styleseed)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/bitjaru/styleseed ↗

All setup options ↓

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Styleseed

Styleseed is a design-method engine that works with AI coding assistants (Claude, Codex, Cursor) to help them make consistent design choices. It includes 23 different agent skills for things like checking design rules, organizing color palettes, and verifying that user interfaces match requirements.

Who it’s for

Developers and design teams who use AI coding tools and want to enforce design consistency automatically. It's open-source, so it's mainly for people comfortable reading and modifying code.

Alternatives

  • Figma plugins: Built-in design-consistency tools directly in Figma. - Storybook: Component library tool that enforces UI consistency without AI. - Zeplin: Design handoff platform with automated style guides. - Design tokens libraries: Tools like Style Dictionary that manage design rules as structured data.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README at https://github.com/bitjaru/styleseed (opens external site) for installation instructions, as the setup method depends on which AI coding assistant and environment you're using.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

33/100
GitHub stars
992
Listing last refreshed
2026-10-30

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Malicious design rules: Someone could hide harmful code inside design rule files that the AI executes without questioning them. - Data in design files: If you point it at design files containing private information (API keys, user data), the AI agent may leak that into outputs. - Prompt injection: Attackers could craft design descriptions that trick the AI into ignoring safety guidelines. - Dependency risks: Like any npm or Python package, this tool depends on other libraries that could be compromised. - Unverified outputs: The skill names mention 'evidence-verified UI' but it's unclear how verification actually works—the AI might still generate incorrect code.

How to lower the risk

Least-privilege permissions

  • Run the tool in a sandbox or isolated project folder, not with full system access.
  • Don't give it access to directories containing secrets or private files.

Network isolation

  • If possible, use it offline or block outbound network requests from the process.
  • Don't connect it to production databases or APIs.

Monitoring

  • Log what design rules and files are being processed.
  • Review the AI's outputs before they reach your codebase.

Red flags to watch for

  • Design rule files from unknown sources or modified unexpectedly.
  • AI generating code that doesn't match the design rules you specified.
  • Sudden new dependencies added to the project.

Questions

How do I install Styleseed?

Styleseed does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/bitjaru/styleseed.

Are there security reports about Styleseed?

No reports found for this package in our research (last checked 2026-10-30). Styleseed currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include malicious design rules.

Is Styleseed actively maintained?

Styleseed has 992 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/bitjaru/styleseed before pinning it in production.

What are alternatives to Styleseed?

Notable alternatives to Styleseed include Figma plugins (Built-in design-consistency tools directly in Figma. - **Storybook**: Component library tool that enforces UI consistency without AI. - **Zeplin**: Design handoff platform with automated style guides. - **Design tokens libraries**: Tools like Style Dictionary that manage design rules as structured data). You can also compare Styleseed side by side with other skills in the Related tools section on this page.

README badge and team notes

Maintain or use Styleseed? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Styleseed

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Styleseed](https://agentarmorhq.com/api/badge/bitjaru-styleseed)](https://agentarmorhq.com/skills/bitjaru-styleseed)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/bitjaru-styleseed"><img src="https://agentarmorhq.com/api/badge/bitjaru-styleseed" alt="AgentArmorHQ Risk Grade for Styleseed" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "bitjaru-styleseed"

Share with your security lead

Need sign-off to use styleseed? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: styleseed
- **Listing URL:** https://agentarmorhq.com/skills/bitjaru-styleseed
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 992 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (bitjaru/styleseed)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/bitjaru/styleseed
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
AI agent skill
Publisher
bitjaru
Source code
github.com/bitjaru/styleseed
Est. context load
~83 tokens idle · ~450 tokens when active (on-demand skill)
Popularity
992 GitHub stars
Last updated
2026-10-30
Last graded
2026-10-23

Community

Discussions for Styleseed

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Styleseed helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude