Ryugi icon

Ryugi

innei/ryugi · v1.101.1 · Agent Skills

by InneiScan grade: GoodAwesome AI Plugins

Agent skills that take a coding agent from brainstorming through an approved spec to test-driven implementation, debugging and UI verification, with a live artboard for comparing mockups and commenting on designs, packaged for Claude Code, Codex, Gemini CLI, OpenCode, Pi and other harnesses

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Ryugi a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Agent Skills
  • Claude Code
  • Antigravity CLI
  • OpenCode
  • Cursor
  • Kimi Code
  • 12 skills
  • Runs hooks on agent events

Before you install

Sign-in
Not declared
Declared access
Interactive, Read, Write
License
SEE LICENSE IN LICENSE

Check before relying on it

  • Some security checks did not finish: Cisco skill scan. See the evidence
  • 2 medium findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.
  • License may restrict use (SEE LICENSE IN LICENSE). Read it before you rely on the plugin.

What is Ryugi?

Ryugi is a published agent skills plugin for AI coding agents that works with Agent Skills, Claude Code, Antigravity CLI, OpenCode, Cursor and Kimi Code, developed by Innei and distributed through the HOL AI plugin registry. Agent skills that take a coding agent from brainstorming through an approved spec to test-driven implementation, debugging and UI verification, with a live artboard for comparing mockups and commenting on designs, packaged for Claude Code, Codex, Gemini CLI, OpenCode, Pi and other harnesses.

Canonical slug
innei/ryugi
Version
v1.101.1 · updated Nov 21, 2026

Registry snapshot

Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
12 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

72

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
76/100
Maintenance
85/100
MCP server setup
100/100
Plugin Security
82/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/Innei/ryugi
Source commit
e5ba9b62c1b1…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Needs review
Security result
82
Security score
0
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
codex:hol-plugin-scanner-QalLZ5 / cisco-skill-scanner: failedcodex:hol-plugin-scanner-QalLZ5 / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

13/16

6 checks

[claude:.] Operational Security

3/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

28/31

9 checks

[codex:.] Security

13/16

9 checks

[codex:.] Operational Security

3/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

5/15

3 checks

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[gemini:.] Gemini Extension

10/10

3 checks

[gemini:.] Security

13/16

6 checks

[gemini:.] Operational Security

3/6

5 checks

[gemini:.] Code Quality

10/10

2 checks

[kimi:.] Kimi Plugin

33/40

10 checks

[opencode:.] OpenCode Plugin

2/2

4 checks

[opencode:.] Security

13/16

6 checks

[opencode:.] Operational Security

3/6

5 checks

[opencode:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

mediummarketplaceMARKETPLACE_SOURCE_INVALID

plugin[0] in marketplace.json must declare "source": {"source": "local", "path": "./plugins/..."}

Use the official repo marketplace shape with a local source object.

mediummarketplaceMARKETPLACE_UNSAFE_SOURCE

The marketplace source "plugin[0]=missing "source.path"" is absolute or resolves outside the plugin directory.

Use relative in-repo paths that stay within the plugin directory.

lowsecuritySECURITY_MD_MISSINGReported 5 times

Plugins should publish a SECURITY.md file for responsible disclosure and support guidance.

Add a SECURITY.md file with reporting guidance and supported versions.

lowoperational-securityDEPENDABOT_MISSINGReported 4 times

Automation or dependency surfaces exist, but .github/dependabot.yml is missing.

Add Dependabot updates for GitHub Actions and dependency manifests.

lowsecurityKIMI_INTERFACE_INVALID

interface must be an object containing string display metadata.

Use string values for Kimi interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Install the plugin

    Installs the ryugi entry from the ryugi-dev marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall ryugi@ryugi-dev.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "author": {
    "name": "Innei",
    "email": "[email protected]",
    "url": "https://github.com/Innei"
  },
  "description": "Ryugi skills for coding agents, plus the artifacts workbench they design in: brainstorming, artboards, documents and TDD.",
  "homepage": "https://github.com/Innei/ryugi",
  "hooks": "./skills/artifacts/app/codex-hooks.json",
  "interface": {
    "displayName": "Ryugi",
    "developerName": "Innei",
    "shortDescription": "Brainstorm on a live artboard, build the approved spec under TDD",
    "longDescription": "Use Ryugi to guide agent work through brainstorming on the Artboard, documents and HTML pages you can comment on, building an approved spec inline under test-driven development, systematic debugging, and isolated worktrees.",
    "category": "Developer Tools",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "I've got an idea for something I'd like to build.",
      "Let's add a feature to this project."
    ],
    "websiteURL": "https://github.com/Innei/ryugi",
    "privacyPolicyURL": "https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement",
    "termsOfServiceURL": "https://docs.github.com/en/site-policy/github-terms/github-terms-of-service",
    "brandColor": "#C65D3B",
    "composerIcon": "./assets/ryugi-small.svg",
    "logo": "./assets/app-icon.png",
    "screenshots": []
  },
  "keywords": [
    "brainstorming",
    "skills",
    "planning",
    "tdd",
    "debugging",
    "code-review",
    "workflow"
  ],
  "license": "SEE LICENSE IN LICENSE",
  "name": "ryugi",
  "repository": "https://github.com/Innei/ryugi",
  "skills": "./",
  "version": "1.101.1",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/Innei/ryugi
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

12 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • isolated-agent-eval

    .claude/skills/isolated-agent-eval/SKILL.md

    Use when an unattended agent session in a test could act on Ryugi Cloud — publish, auto-publish, or use a Cloud sign-in — including writing-skills baseline and with-skill runs and pressure scenarios that use artifacts with `--auto-approve`.

    Raw SKILL.md
  • writing-skills

    .claude/skills/writing-skills/SKILL.md

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

    Raw SKILL.md
  • artifacts

    skills/artifacts/SKILL.md

    Use when seeing decides faster than reading — UI directions or mockups to choose between, a page to tune or click through, a design doc, review, proposal, or architecture walkthrough for them or their team to read — or when they ask for an artifact or artboard by name, or for a link to share one, or when they paste a Ryugi Cloud link (…/a/…) to read, including during brainstorming.

    Raw SKILL.md
  • brainstorming

    skills/brainstorming/SKILL.md

    You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

    Raw SKILL.md
  • design-system

    skills/design-system/SKILL.md

    Use when a project without its own design system needs several screens or a whole UI designed, when its screens exist but its style values are scattered with no tokens, when only a product doc exists and the UI is about to be designed, or when your human partner asks to build, rebuild or refresh a design system, design tokens or a visual language.

    Raw SKILL.md
  • executing-specs

    skills/executing-specs/SKILL.md

    Use when an approved spec or design document is ready to implement and your human partner chose inline execution, or when they point you at a written design and ask you to build it in this session

    Raw SKILL.md
  • interface-craft

    skills/interface-craft/SKILL.md

    Use when a visible product interface needs design judgment, including UI mockups during brainstorming, landing and marketing pages, visual direction exploration, reviewing an existing screen, or refining a prototype that feels generic or inconsistent.

    Raw SKILL.md
  • systematic-debugging

    skills/systematic-debugging/SKILL.md

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Raw SKILL.md
  • test-driven-development

    skills/test-driven-development/SKILL.md

    Use when implementing any feature or bugfix, before writing implementation code

    Raw SKILL.md
  • using-git-worktrees

    skills/using-git-worktrees/SKILL.md

    Use when ryugi:executing-specs or ryugi:test-driven-development sends you here before the first implementation edit, when uncommitted work has to move to or be committed on a branch other than the one checked out, or when work done in a worktree has landed

    Raw SKILL.md
  • using-ryugi

    skills/using-ryugi/SKILL.md

    Use when starting any conversation - routes each task to the Ryugi workflow for its stage

    Raw SKILL.md
  • verifying

    skills/verifying/SKILL.md

    Use before telling your human partner that work is done, fixed, live or ready, whatever it touched — UI, an API, a CLI, data, a deploy, performance — and before fixing a bug they can see, to capture it first

    Raw SKILL.md

File inventory

.agents/plugins/marketplace.json

file

345 bytes

9f4712cd00a03e92…

.claude-plugin/marketplace.json

file

932 bytes

52b3c2f507466ebb…

.claude-plugin/plugin.json

file

486 bytes

0bdf927d388aa841…

.claude/skills/isolated-agent-eval/docker/entrypoint.sh

file

2,052 bytes

5d60906e002d6d81…

.claude/skills/isolated-agent-eval/provider-config.py

file

1,062 bytes

f2cf5dc230ed71d2…

.claude/skills/isolated-agent-eval/run.sh

file

3,784 bytes

ec76c0a7bf8d2ec7…

.claude/skills/isolated-agent-eval/SKILL.md

skill

5,393 bytes

342119085e92401f…

.claude/skills/writing-skills/anthropic-best-practices.md

file

46,191 bytes

ba624ee7559ca1bb…

.claude/skills/writing-skills/examples/CLAUDE_MD_TESTING.md

file

5,434 bytes

b8f40fe5136e7ffb…

.claude/skills/writing-skills/persuasion-principles.md

file

6,136 bytes

28d7e590416678eb…

.claude/skills/writing-skills/render-graphs.js

file

5,035 bytes

70ecc0f13cbaa708…

.claude/skills/writing-skills/SKILL.md

skill

28,021 bytes

8b002525bc9cf0cf…

.claude/skills/writing-skills/testing-skills-with-subagents.md

file

13,138 bytes

b93363b99c57faae…

.codex-plugin/plugin.json

plugin-manifest

1,535 bytes

647ec6d41c482157…

.cursor-plugin/plugin.json

file

577 bytes

425a6687fd8fa648…

.kimi-plugin/plugin.json

file

3,026 bytes

17756d69e9e54cd4…

.opencode/plugins/ryugi.js

file

17,688 bytes

76b7b328db8ff7a3…

AGENTS.md

file

4,933 bytes

bce3b18b8c63e89f…

assets/app-icon.png

asset

56,672 bytes

b9027de050c1b1f9…

assets/ryugi-small.svg

asset

1,523 bytes

1beb562f236006f7…

eslint.config.mjs

file

873 bytes

8b97b4731546f020…

gemini-extension.json

file

222 bytes

ed1a3de4511e3b42…

GEMINI.md

file

80 bytes

a1c01e7021bc7cd8…

hooks/flush-artifacts.cjs

file

1,383 bytes

131df10e0a428efd…

hooks/hooks-antigravity.json

file

1,076 bytes

4db29dbf49d2a993…

hooks/hooks-cursor.json

file

137 bytes

6a57b9bd4e732862…

hooks/hooks.json

file

3,789 bytes

0f8f06bffd428c2a…

hooks/project-root.sh

file

1,197 bytes

71a708024b56c975…

hooks/selection-context.cjs

file

19,762 bytes

ecc20e9223cbb25c…

hooks/start-artifacts.cjs

file

2,396 bytes

017bee32cc386d2e…

hooks/watch-comments.cjs

file

185 bytes

255b1a390cdfbd08…

LICENSE

file

15,708 bytes

ce0021a0482a0a84…

package.json

file

1,513 bytes

2f6cfbde1841d52f…

pnpm-lock.yaml

file

190,957 bytes

f86693f922e5ac80…

README.md

file

12,941 bytes

8a30c80beaa8f456…

skills/artifacts/app/agent-event.cjs

skill

7,121 bytes

5ba06b3e28722390…

skills/artifacts/app/agy-comment-watch.cjs

skill

9,338 bytes

8cf225442571b579…

skills/artifacts/app/codex-comment-watch.cjs

skill

9,205 bytes

262008b9dcc72b69…

skills/artifacts/app/codex-desktop-transport.cjs

skill

7,132 bytes

25f7a5fec1763c05…

skills/artifacts/app/codex-hooks.json

skill

3,032 bytes

4f893aa980e5047a…

skills/artifacts/app/comment-subscriptions.cjs

skill

12,479 bytes

ee0d4708aa7f0edd…

skills/artifacts/app/comment-threads.cjs

skill

1,354 bytes

6afbf202c4da96cb…

skills/artifacts/app/comment-watch.cjs

skill

17,606 bytes

a95c9d2bd7b43f88…

skills/artifacts/app/output-bootstrap.cjs

skill

34,061 bytes

f6f224b713961e53…

skills/artifacts/app/ryugi-artifacts.cjs

skill

128 bytes

21265d7c40e8e1e1…

skills/artifacts/app/ryugi.cjs

skill

9,404 bytes

9769cd7a2d56c073…

skills/artifacts/examples/today-inbox.html

skill

6,351 bytes

db585c5f118b15cb…

skills/artifacts/SKILL.md

skill

9,113 bytes

fbfab590431c33a2…

skills/brainstorming/artboard-rounds.md

skill

3,514 bytes

787337333e2abbca…

skills/brainstorming/builder-check-prompt.md

skill

1,081 bytes

ac4e70a49feb2cf6…

skills/brainstorming/doc-rounds.md

skill

5,339 bytes

b6786de745f2278a…

skills/brainstorming/SKILL.md

skill

12,276 bytes

7df276e8941ed2d6…

skills/brainstorming/written-design.md

skill

2,683 bytes

bbee75a4bd054025…

skills/design-system/checks.md

skill

2,194 bytes

db0c95ecc62fcf79…

skills/design-system/examples/DESIGN.md

skill

2,586 bytes

16df74cb74306311…

skills/design-system/examples/tokens.css

skill

2,236 bytes

5959c415d2a03285…

skills/design-system/examples/tokens.json

skill

2,865 bytes

eacc0a4ff2e9ec14…

skills/design-system/landing.md

skill

2,381 bytes

580936978087d71c…

skills/design-system/platforms/ios.md

skill

1,510 bytes

88b113d067d2c46e…

skills/design-system/SKILL.md

skill

8,057 bytes

344694e0eaac5191…

skills/design-system/stages.md

skill

7,761 bytes

ca77cf3312da5186…

skills/executing-specs/code-reviewer.md

skill

3,753 bytes

f538f21f71061b6d…

skills/executing-specs/exploring.md

skill

947 bytes

fd8553dda1d914b5…

skills/executing-specs/landing.md

skill

1,088 bytes

7e5f2543573e133a…

skills/executing-specs/SKILL.md

skill

15,985 bytes

5e96ee225631618a…

skills/interface-craft/references/direction.md

skill

3,517 bytes

6200f31aa8d4e513…

skills/interface-craft/references/evaluation.md

skill

4,590 bytes

c515c29ee7703540…

skills/interface-craft/references/signs.md

skill

8,748 bytes

dce5bf23fc8d936a…

skills/interface-craft/references/tokens.md

skill

7,368 bytes

da7abcd65fdd0e7f…

skills/interface-craft/SKILL.md

skill

5,711 bytes

dadba4ef0e116a52…

skills/systematic-debugging/condition-based-waiting-example.ts

skill

5,059 bytes

40bd9c5028f8b448…

skills/systematic-debugging/condition-based-waiting.md

skill

3,699 bytes

8fa13127aab996d9…

skills/systematic-debugging/CREATION-LOG.md

skill

4,271 bytes

c4e482ebb656e8ea…

skills/systematic-debugging/defense-in-depth.md

skill

3,642 bytes

a39a2a6727b928c3…

skills/systematic-debugging/find-polluter.sh

skill

1,986 bytes

dd7b8f13c4cc2a24…

skills/systematic-debugging/root-cause-tracing.md

skill

6,109 bytes

90444c86e4bcf802…

skills/systematic-debugging/SKILL.md

skill

8,526 bytes

5034ce53990b82e3…

skills/systematic-debugging/test-academic.md

skill

653 bytes

fe2ba480d78ac0d6…

skills/systematic-debugging/test-pressure-1.md

skill

1,907 bytes

3e41339d11da0859…

skills/systematic-debugging/test-pressure-2.md

skill

2,290 bytes

8f560afcf8f65d9e…

skills/systematic-debugging/test-pressure-3.md

skill

2,698 bytes

09ce570d57beef49…

skills/test-driven-development/SKILL.md

skill

7,837 bytes

d265d67b5214de5f…

skills/test-driven-development/writing-good-tests.md

skill

8,656 bytes

d9c3377bcef26db9…

skills/using-git-worktrees/SKILL.md

skill

11,958 bytes

58f3dce58d98f4c5…

skills/using-ryugi/references/antigravity-tools.md

skill

7,165 bytes

17453cf2969bf0ae…

skills/using-ryugi/references/claude-code-tools.md

skill

209 bytes

763aa87b39df7ced…

skills/using-ryugi/references/codex-tools.md

skill

4,690 bytes

954add076fd11b40…

skills/using-ryugi/references/gemini-tools.md

skill

8,309 bytes

d63ab4593f21ed8b…

skills/using-ryugi/references/hermes-tools.md

skill

2,718 bytes

25500ceeaa3be3cc…

skills/using-ryugi/references/muse-tools.md

skill

3,056 bytes

cbdbd31885a85ac0…

skills/using-ryugi/references/pi-tools.md

skill

1,516 bytes

f88994251e14f230…

skills/using-ryugi/SKILL.md

skill

2,824 bytes

7e6dd9a183f89bc8…

skills/verifying/pages.md

skill

4,412 bytes

ad09631298bde910…

skills/verifying/SKILL.md

skill

10,104 bytes

ac93d0a9f4055c3b…

skills/verifying/verdicts.md

skill

2,562 bytes

38fc83d3c3a282fa…

Ryugi — Frequently asked questions

What is Ryugi?
Ryugi is an AI plugin in the HOL registry. Agent skills that take a coding agent from brainstorming through an approved spec to test-driven implementation, debugging and UI verification, with a live artboard for comparing mockups and commenting on designs, packaged for Claude Code, Codex, Gemini CLI, OpenCode, Pi and…
How do I install Ryugi?
Install Ryugi in your harness: Claude Code — /plugin marketplace add Innei/ryugi; Cursor — npx [email protected] add Innei/ryugi; Antigravity CLI — npx [email protected] add Innei/ryugi. Full step-by-step guidance is on the HOL plugin page.
How do I install Ryugi in HOL Guard?
To install Ryugi in HOL Guard, start with hol-guard plugin install innei/ryugi --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Ryugi in Claude Code?
To install Ryugi in Claude Code, start with /plugin marketplace add Innei/ryugi. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install Ryugi in Cursor?
To install Ryugi in Cursor, start with npx [email protected] add Innei/ryugi. The complete step-by-step install guide for Cursor is on the HOL plugin page.
How is the Trust Score for Ryugi computed?
Ryugi has a HOL Trust Score of 72 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/innei%2Fryugi/trust
Who publishes Ryugi?
Ryugi is published by Innei and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Reviews and similar plugins