agentmods.dev

verify-design-skill

verify-design-skill is a skill for Claude Code, Codex from TudeOrangBiasa/design-skill. It costs 49 tokens per session (391 once invoked), scanned A, original, Apache-2.0.

A verification skill for driving the design-skill command-line tool and collecting JSON evidence. It runs detection, design validation, and design checks against prepared test files.

In plain words
What is it for?
Use it before a pull request that changes the design-skill scripts, rules, or command catalog. It covers checking help output, detecting problems in HTML fixtures, validating design documents, and saving smoke-test results.
Why use it?
It gives contributors repeatable checks for the design dispatcher instead of relying on manual inspection. The saved evidence shows whether commands ran and whether their reported findings match expectations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 9repo 3d ago A scan 49 tokens original Apache-2.0

Good fit Use it before a pull request that changes the design-skill scripts, rules, or command catalog. It covers checking help output, detecting problems in HTML fixtures, validating design documents, and saving smoke-test results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tudeorangbiasa/design-skill/verify-design-skill
View source ↗ TudeOrangBiasa/design-skill
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.

Any agent
npx skills add TudeOrangBiasa/design-skill --skill verify-design-skill
Clone the repo
git clone --depth 1 https://github.com/TudeOrangBiasa/design-skill

Made for: Claude Code, Codex.

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 verify-design-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/tudeorangbiasa/design-skill/verify-design-skill/github.svg)](https://agentmods.dev/skills/tudeorangbiasa/design-skill/verify-design-skill)
Your own site
<a href="https://agentmods.dev/skills/tudeorangbiasa/design-skill/verify-design-skill"><img src="https://agentmods.dev/badge/skills/tudeorangbiasa/design-skill/verify-design-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify-design-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/tudeorangbiasa/design-skill/verify-design-skill"><img src="https://agentmods.dev/badge/skills/tudeorangbiasa/design-skill/verify-design-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00391
Opus 5.5 $0.00020 $0.00156
Sonnet 5.5 $0.00010 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 2d ago against content hash 1f9cd4e37ebd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-design-skill 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/smoke.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/verify-design-skill/SKILL.md · 36 lines

What it actually says

Verify design-skill

Primary surface: the design CLI (scripts/design.mjs, bin design-skill). Secondary: SKILL.md docs read by agents (gated by npm run lint:docs).

Launch

No server and no install step. The scripts have no dependencies. Run node scripts/design.mjs <tool> ... from the repo root.

Doctor

node scripts/design.mjs --help prints Usage: design <tool> [args...] and the tool list. If it doesn't, the dispatcher or scripts/command-metadata.json is broken.

Drive

  • node scripts/design.mjs detect scripts/fixtures/slop.html --json: summary.total > 0, and findings.length equals summary.total.
  • node scripts/design.mjs detect scripts/fixtures/new-slop.html --json covers the 2025-2026 tells.
  • node scripts/design.mjs validate <DESIGN.md> and check-design cover the fixtures under scripts/fixtures/design-system/.

Evidence

bash skills/verify-design-skill/scripts/smoke.sh saves help.txt and detect-slop.json under .scratch/verify/<run>/ and prints the finding counts.

Cleanup

Nothing is left running, and evidence stays in .scratch/verify/. Delete .scratch/ whenever you like.

Helpers

  • skills/verify-design-skill/scripts/smoke.sh (the "CLI smoke" step of scripts/verify.sh).
  • Feature map: features/README.md.
Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 36 lines · 49 tokens per session scan A 1f9cd4e37ebd

Subscribe to this mod's changes

verify-design-skill is a skill published in the GitHub repository TudeOrangBiasa/design-skill (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 391 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-04.

DebuggingTesting
Related

verify-design-skill compared with skills from other repositories

verify-design-skill next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verify-design-skillTudeOrangBiasa/design-skillSkill93d agoApache-2.0A49Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadataSkill16kyesterdayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7k3d agoMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill319yesterdayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skillsSkill1.9k23d agoMITA36Claude Code
triaging-web-analytics-supportPostHog/posthogSkill41kyesterdaynoneA151Claude Code, Codex