apexyard: Skill for Claude Code

.claude/skills/approve-design/SKILL.md

approve-design is a skill for Claude Code from me2resh/apexyard. It costs 26 tokens per session (2,717 once invoked), scanned A, original, MIT.

A record-keeping step for confirming that a specific pull request passed design review. A pull request is a proposed code change waiting to be merged.

In plain words
What is it for?
Recording approval for pull requests that change interface files such as React components, Vue files, stylesheets, or design tokens.
Why use it?
It gives a UI merge gate evidence that a designer approved the visual changes for that exact pull request and commit.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

This is me2resh/apexyard's own configuration. It tells Claude Code how to work on apexyard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything apexyard configures →

Reuse

Borrowing it

Nothing to install: this file belongs to me2resh/apexyard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/me2resh/apexyard/main/.claude/skills/approve-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/me2resh/apexyard

Made for: Claude Code.

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 approve-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/me2resh/apexyard/approve-design/github.svg)](https://agentmods.dev/skills/me2resh/apexyard/approve-design)
Your own site
<a href="https://agentmods.dev/skills/me2resh/apexyard/approve-design"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/approve-design/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 approve-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/me2resh/apexyard/approve-design"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/approve-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,717 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00026 $0.02717
Opus 5 $0.00013 $0.01358
Sonnet 5 $0.00005 $0.00543
Haiku 4.5 $0.00003 $0.00272

Measured 9d ago against content hash 3a2dced9c15d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

approve-design 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 9d 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.

.claude/skills/approve-design/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/approve-design - Record Per-PR Design-Review Approval

Writes .claude/session/reviews/<owner>__<repo>__<pr>-design.approved (repo-qualified path, see AgDR-0060) with the current HEAD SHA so the require-design-review-for-ui.sh merge-gate hook will let a UI PR through. Without this marker, the hook blocks merges on any PR that touches .tsx, .jsx, .vue, .svelte, .css, .scss, .sass, .less, or design-tokens* files.

This skill is the design-review analog of /approve-merge (which writes the CEO marker for the merge gate). Same pattern, different gate.

The one rule you must not break

INVOKE THIS SKILL ONLY ON EXPLICIT, PER-PR, DESIGN-REVIEW APPROVAL.

The valid invocation triggers look like this:

  • "design approved" / "UI looks good" / "design review passed" — if and only if the surrounding context clearly names a specific PR and the designer has actually reviewed the PR's visual changes.
  • "PR #42 design approved" / "the UI in #42 looks right" — names the PR explicitly.
  • A reply to your own "PR #42 has UI changes — design review approved?" message that consists of any affirmative token — because you just named the PR and the user/designer is responding to that specific question.

Invalid triggers (do NOT run this skill):

  • "looks good" / "nice" / "approved" — when said about a Figma mockup, a design spec, a screenshot, or any artifact that is not a specific PR's diff. Design review means reviewing the actual code changes in a PR, not a mockup. A mockup approval and a PR approval are different moments.
  • "the design is fine" — when said in a planning context ("let's go with this design approach") rather than a PR-review context ("I've looked at the PR diff and the implementation matches the design"). The skill is for the latter.
  • "go" / "continue" / "ship it" — when these are umbrella responses to a multi-step plan. Same rule as /approve-merge.
  • Your own inference that "the designer probably approves because they liked the mockup earlier." NO. Mockup approval ≠ implementation approval. Stop and ask.

Read the full file on GitHub · 188 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.

  1. 9d ago First seen · 188 lines · 26 tokens per session scan A 3a2dced9c15d

Subscribe to this mod's changes

approve-design is a skill published in the GitHub repository me2resh/apexyard (498 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 2,717 once invoked, about $0.0001 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.