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.
npx skills add me2resh/apexyard --skill approve-designgit clone --depth 1 https://github.com/me2resh/apexyardWrote 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.
[](https://agentmods.dev/skills/me2resh/apexyard/approve-design)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.03303 |
| Opus 5.5 | $0.00010 | $0.01321 |
| Sonnet 5.5 | $0.00005 | $0.00661 |
| Haiku 4.5 | $0.00003 | $0.00330 |
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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.
/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 a UI file — the pattern list lives in .claude/hooks/_lib-ui-paths.sh (React/Vue/Svelte/Astro/MDX components, template-engine files, styles, and design tokens), shared with step 5 below so the two checks never diverge (me2resh/apexyard#1390).
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.
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.
- 22d ago Changed · +20 lines 9c18e92c2308
- 1mo ago Changed · +11 lines c9fa3a23f24c
- 1mo ago Changed · +4 lines b19191247fa0
- 2mo ago First seen · 188 lines · 26 tokens per session scan A 3a2dced9c15d
approve-design is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 3,303 once invoked, about $0.0001 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 2026-08-30.
approve-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| approve-designme2resh/apexyard | Skill | 542 | yesterday | MIT | A | 26 | Claude Code |
| aesthetic-instrumentavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 106 | Claude Code |
| committed-aestheticavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 94 | Claude Code |
| anydesignavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 214 | Claude Code |
| ui-ux-pro-maxavelikiy/great_cto | Skill | 112 | 2d ago | MIT | B | 238 | Claude Code |
| quality-reviewParetofilm/superpowers-gstack | Skill | 3 | 2d ago | none | B | 54 | Claude Code |
| ln-13-interaction-design-builderlevnikolaevich/claude-code-skills | Skill | 587 | yesterday | MIT | A | 30 | Claude Code |