U

unslop

vibefoundry/unslop · v2.1.1 · Development & Workflow

by VibeFoundryScan grade: Good

MCP server: UI and CSS design linter with 72 rules and 4 tools that audits AI-generated front-end code and generates refactor plans

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 unslop a fit?

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

Works with

  • MCP
  • Claude Code
  • 3 skills
  • 2 MCP servers

Before you install

Sign-in
Not declared
Declared access
Interactive, Read
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence
  • 3 high or critical findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is unslop?

unslop is a published development & workflow plugin for AI coding agents that works with MCP and Claude Code, developed by VibeFoundry and distributed through the HOL AI plugin registry. MCP server: UI and CSS design linter with 72 rules and 4 tools that audits AI-generated front-end code and generates refactor plans.

Canonical slug
vibefoundry/unslop
Version
v2.1.1 · updated Nov 18, 2026

Registry snapshot

Owner verification
Not verified
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
3 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

35

HOL Trust Score

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

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
80/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/avivgerz-hue/unslop
Source commit
ca9a3969233e…
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
80
Security score
3
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
codex:hol-plugin-scanner-rTOe5s / cisco-skill-scanner: failedcodex:hol-plugin-scanner-rTOe5s / cisco-mcp-scanner: unavailable

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

20/20

6 checks

[claude:.] Operational Security

12/20

5 checks

[claude:.] Code Quality

5/10

2 checks

[codex:.] Manifest Validation

28/31

9 checks

[codex:.] Security

20/20

9 checks

[codex:.] Operational Security

12/20

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

5/10

2 checks

[opencode:.] OpenCode Plugin

5/5

4 checks

[opencode:.] Security

20/20

6 checks

[opencode:.] Operational Security

12/20

5 checks

[opencode:.] Code Quality

5/10

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

highcode-qualityDANGEROUS_DYNAMIC_EXECUTIONReported 3 times

tests/discovery.test.ts: new Function() uses eval() or new Function().

Remove dynamic code evaluation and replace it with explicit control flow.

mediumoperational-securityGITHUB_ACTION_UNPINNEDReported 18 times

.github/workflows/ci.yml references "actions/checkout@v4" instead of a full 40-character commit SHA.

Pin third-party GitHub Actions and reusable workflows to a full commit SHA.

mediumoperational-securityGITHUB_ACTION_UNPINNEDReported 9 times

.github/workflows/ci.yml references "actions/setup-node@v4" instead of a full 40-character commit SHA.

Pin third-party GitHub Actions and reusable workflows to a full commit SHA.

mediumoperational-securityGITHUB_ACTION_UNPINNEDReported 3 times

.github/workflows/ci.yml references "actions/setup-go@v5" instead of a full 40-character commit SHA.

Pin third-party GitHub Actions and reusable workflows to a full commit SHA.

lowoperational-securityDEPENDABOT_MISSINGReported 3 times

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

Add Dependabot updates for GitHub Actions and dependency manifests.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

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

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

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

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

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

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

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

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

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

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

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

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

    Find the marketplace and plugin names

    The install id is <plugin-entry>@<marketplace-name>, and the marketplace name is declared inside the manifest — it can differ from the repository name. List registered marketplaces to read both names.

    shell
  3. 3

    Install the plugin

    Substitute the plugin entry name and the marketplace name shown by the previous step.

    claude code

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

{
  "name": "unslop",
  "version": "2.1.1",
  "description": "Seven-pillar UI/UX design craft audits, studio archetypes and exact transformation blueprints for AI-generated interfaces, with 72 rules and 4 MCP tools.",
  "author": {
    "name": "VibeFoundry",
    "url": "https://github.com/avivgerz-hue"
  },
  "homepage": "https://github.com/avivgerz-hue/unslop#readme",
  "repository": "https://github.com/avivgerz-hue/unslop",
  "license": "MIT",
  "keywords": [
    "ui",
    "ux",
    "design",
    "linter",
    "mcp",
    "accessibility",
    "agent-skills"
  ],
  "interface": {
    "displayName": "unslop",
    "developerName": "VibeFoundry",
    "shortDescription": "72-rule UI/UX design linter for AI-generated apps",
    "category": "Coding",
    "websiteURL": "https://github.com/avivgerz-hue/unslop",
    "longDescription": "Seven-pillar UI/UX design craft audits, studio archetypes and exact transformation blueprints, exposed as an MCP server with 72 rules and 4 tools.",
    "capabilities": [
      "Interactive",
      "Read"
    ]
  },
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/avivgerz-hue/unslop
Marketplace path
Unknown
Source path
.
Install policy
Unspecified

Skills

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

Share
skills-cli
  • unslop

    .agents/skills/unslop/SKILL.md

    Enforce the Linear Precision design system and eliminate generic AI UI slop. Use when building, refactoring, or reviewing frontend interfaces.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • unslop

    .claude/skills/unslop/SKILL.md

    Enforce the Linear Precision design system and eliminate generic AI UI slop. Use when building, refactoring, or reviewing frontend interfaces.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

  • unslop

    SKILL.md

    Principal UI/UX Design Engineer protocol for Claude Code, Cursor, and Windsurf. Diagnose 72 anti-slop rules across 7 pillars, install one of 10 studio archetypes or extracted Design DNA, generate an exact transformation blueprint, and verify interfaces to 95–100/100 (A+).

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.agents/skills/unslop/SKILL.md

skill

14,266 bytes

a5178654c0f8e418…

.claude-plugin/plugin.json

file

396 bytes

8a15dedec30cea9c…

.claude/skills/unslop/SKILL.md

skill

14,266 bytes

a5178654c0f8e418…

.clinerules

file

14,086 bytes

42199d843801f072…

.codex-plugin/plugin.json

plugin-manifest

1,009 bytes

47ba81e2755e09bd…

.cursor/mcp.json

file

148 bytes

d7e2bdbb841cebad…

.cursor/rules/unslop.mdc

file

14,261 bytes

f893d7655bfc1676…

.cursorrules

file

14,086 bytes

42199d843801f072…

.github/copilot-instructions.md

file

14,086 bytes

42199d843801f072…

.github/workflows/ci.yml

file

6,222 bytes

b4c83cddcfbed674…

.mcp.json

file

148 bytes

d7e2bdbb841cebad…

.registry/mcp.json

mcp-config

189 bytes

6520f6a6678dc918…

.vscode/mcp.json

file

168 bytes

e13417d32427d4ae…

.zed/settings.json

file

189 bytes

87c8e23fa759a7b9…

AGENTS.md

file

14,086 bytes

42199d843801f072…

assets/demo.svg

asset

4,844 bytes

73194ec45cd5e2a0…

assets/hero-preview.svg

asset

18,076 bytes

e754681f06c98a62…

bin/unslop.ts

file

17,030 bytes

05b54ac5ba22cd4d…

CLAUDE.md

file

14,086 bytes

42199d843801f072…

CONTRIBUTING.md

file

5,607 bytes

fa434c2c7534ea1d…

glama.json

file

7,797 bytes

ef7b96831b987cdd…

LICENSE

file

1,424 bytes

10b768454a2bc7da…

llms.txt

file

2,759 bytes

f97480edb38aafe9…

opencode.json

file

233 bytes

da6687d498a53399…

package-lock.json

file

75,191 bytes

952fde01fdee1666…

package.json

file

3,124 bytes

095014bdec70ae14…

README.md

file

19,484 bytes

8a84e143300a93da…

scripts/build.mjs

file

2,713 bytes

13eebaf19ef002a8…

SECURITY.md

file

1,109 bytes

5de9ec8048f55786…

server.json

file

3,547 bytes

bd96bbfd1cec6304…

SKILL.md

skill

17,534 bytes

2a56e2118a46d464…

smithery.yaml

file

236 bytes

20e444e6d3f6df3b…

src/analyzer/design-craft.ts

file

42,398 bytes

d6039bceb89a8aaf…

src/analyzer/refactor-plan.ts

file

14,789 bytes

3abb9b50d28ae077…

src/analyzer/slop-detector.ts

file

41,098 bytes

49c72e62d3a94c96…

src/analyzer/wcag.ts

file

7,181 bytes

e5d810954aa7b817…

src/extractor/extract-dna.ts

file

33,719 bytes

00d5b83e4b3c71d5…

src/mcp/server.ts

file

17,543 bytes

509132d4f03a95be…

src/presets/anthropic-warm-editorial.json

file

3,753 bytes

4ed8f477f6758f45…

src/presets/apple-glass.json

file

3,206 bytes

d13723b9ac1af646…

src/presets/bloomberg-terminal-dense.json

file

3,075 bytes

93b2d62031afbb52…

src/presets/fintech-institutional.json

file

3,354 bytes

5f4773502f4d7c2b…

src/presets/index.ts

file

12,121 bytes

3f2d35c6525c573a…

src/presets/linear-dark.json

file

2,949 bytes

30608c68d4da018d…

src/presets/linear-precision.json

file

3,320 bytes

795c779a74e76eac…

src/presets/neo-brutalist-craft.json

file

3,742 bytes

dd14cf89c9952dcf…

src/presets/neo-brutalist.json

file

2,621 bytes

743f9da342a5bac9…

src/presets/raycast-command.json

file

3,330 bytes

8ebb723c7a67f23d…

src/presets/stripe-atmospheric.json

file

3,689 bytes

fd0fcdff85abd012…

src/presets/stripe-minimal.json

file

3,000 bytes

5711b68ab226a2b9…

src/presets/swiss-editorial.json

file

3,717 bytes

3535653c5b807c8d…

src/presets/swiss-grid.json

file

2,596 bytes

0cc142d0e722f2a2…

src/presets/teenage-engineering.json

file

3,538 bytes

a2ed73c2acbe6306…

src/presets/vercel-monochrome.json

file

3,543 bytes

60e4df0394947e0a…

src/sync/rule-writer.ts

file

22,162 bytes

e047734078e43b87…

src/sync/token-exporter.ts

file

15,294 bytes

81f2a2ffbb1e4dfb…

src/sync/transformation-rules.ts

file

4,734 bytes

692052c675ee98e6…

src/version.ts

file

308 bytes

0b1d67f9b7f707eb…

tests/discovery.test.ts

file

9,599 bytes

2d4f53c157b2f5d3…

tests/fixtures/demo/after/Hero.tsx

file

323 bytes

cb284cc79e01e186…

tests/fixtures/demo/before/Hero.tsx

file

130 bytes

61dcc77dd20767e1…

tests/footer.test.ts

file

3,584 bytes

9065c18c4f4740b4…

tests/integrations.test.ts

file

7,923 bytes

ea310d6042a64062…

tests/readme-demo.test.ts

file

3,219 bytes

f4c980a176b5d166…

tests/unslop.test.ts

file

28,073 bytes

d486ccb134eed287…

tests/v1-1.test.ts

file

16,271 bytes

bebab6689b0a842e…

tests/v2.test.ts

file

19,099 bytes

42a8bb98c65fe0a8…

tsconfig.json

file

719 bytes

ffba1ac5a0f10a06…

unslop — Frequently asked questions

What is unslop?
unslop is an AI plugin in the HOL registry. MCP server: UI and CSS design linter with 72 rules and 4 tools that audits AI-generated front-end code and generates refactor plans.
How do I install unslop?
Install unslop in your harness: Claude Code — /plugin marketplace add avivgerz-hue/unslop; MCP — git clone https://github.com/avivgerz-hue/unslop; Any agent — npx [email protected] add avivgerz-hue/unslop. Full step-by-step guidance is on the HOL plugin page.
How do I install unslop in Claude Code?
To install unslop in Claude Code, start with /plugin marketplace add avivgerz-hue/unslop. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install unslop in MCP?
To install unslop in MCP, start with git clone https://github.com/avivgerz-hue/unslop. The complete step-by-step install guide for MCP is on the HOL plugin page.
How is the Trust Score for unslop computed?
unslop has a HOL Trust Score of 35 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/vibefoundry%2Funslop/trust
Who publishes unslop?
unslop is published by VibeFoundry 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