render-audit

render-audit is a skill for Claude Code from laguna821/Achmage-Skills. It costs 221 tokens per session (2,595 once invoked), scanned A, original, Apache-2.0.

A quality checker for rendered frontend pages, meaning pages after a browser has laid them out and displayed them. It measures structure, pixel contrast, visual coverage, and screenshots at several widths and color themes.

In plain words
What is it for?
Use it for full or declared fast audits of live previews and HTML decks, then rerun it after fixes.
Why use it?
It separates measurable display problems from personal design opinions and makes reduced checks explicit.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the render-audit plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/laguna821/achmage-skills/render-audit
Any agent
npx skills add laguna821/Achmage-Skills --skill render-audit
Clone the repo
git clone --depth 1 https://github.com/laguna821/Achmage-Skills

Made for: Claude Code.

Or install render-audit, the plugin that ships this one along with the rest of its 1 skill.

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 render-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/laguna821/achmage-skills/render-audit.svg)](https://agentmods.dev/skills/laguna821/achmage-skills/render-audit)
Your own site
<a href="https://agentmods.dev/skills/laguna821/achmage-skills/render-audit"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/render-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00221 $0.02595
Opus 5 $0.00111 $0.01298
Sonnet 5 $0.00044 $0.00519
Haiku 4.5 $0.00022 $0.00260

Measured 6d ago against content hash 2e3970b6b615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

render-audit 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/render-qa-harness.js), 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.

Design-Consulting/render-audit/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Render Audit — 렌더 실측 검사관

직무 선언. 이 스킬은 검사관(auditor) 이다 — 처방하지 않고, 빌드하지 않고, 수리하지 않는다. 렌더된 픽셀을 실측하고 판정만 내린다. 수리는 호출자(빌드 세션)의 일이고, 이 스킬은 수리 후 재검사로 돌아온다. 계보: component-consulting-v3 [[component-consulting-v3]] Step 7.5 에서 v3.6 때 분리 (한 스킬에 컨설턴트와 검사관 두 직무가 묶여 있던 §5 자기모순의 해소). 이제 OS 공용 — 어떤 프론트엔드 빌드 세션이든 호출할 수 있다.

§0 — 발동 (when this skill runs)

  1. 인수인계 계약 (자동·블로킹)component-consulting-v3 [[component-consulting-v3]] 의 처방문에는 § Render QA 인수인계 계약이 있다 (RAW OK 와 동급의 HARD 계약). 그 처방을 빌드하는 세션은 완료 선언 전에 이 스킬의 full 검사를 반드시 실행한다 — 계약 불이행 = 완료 선언 금지.
  2. 빌드 완료 직전 (자동) — 처방 출신이 아니어도, OS 안에서 프론트엔드 산출물(라이브 페이지·HTML 덱)이 "완료" 로 선언되기 직전이 발동 시점이다. 렌더 가능한 산출물에 검사 없는 완료 선언은 없다.
  3. 사용자 직접 호출 — "렌더 검사", "render QA", "이 페이지 실측 검사해줘".

전제: 산출물이 로컬 프리뷰에서 렌더된 상태. 빌드 없는 처방-전용 세션에서는 발동하지 않는다 — 그 세션은 스킵을 선언하고, 빌드 세션이 계약을 승계한다.

§1 — 모드: full 이 기본값이다

모드 내용 발동
full (기본) RQ1 3폭(375/768/1440) × 2스킴(light/dark) + RQ2ALL + RQOBSALL + RQ3 섹션×스킴 매트릭스 전수 자동 — 선언 불요
fast 축소 조합 (예: 1440 라이트 + 다크 스팟) 명시 선언 시에만

fast 는 선언식 예외다 — "조용한 압축 금지"(v3 Step 7 처방 완결성 게이트)와 동형: 강도 하향은 금지가 아니라 선언 대상이다. fast 로 가려면 검사 보고서 머리에 3가지를 쓴다:

  1. 근거 — 왜 축소하는가 (예: 단일 섹션 핫픽스 재검).
  2. 생략 조합 열거 — 안 돈 폭×스킴×계층을 전부 나열.
  3. 잔여 리스크 1줄 — 생략이 못 잡는 결함 부류.

선언 없는 축소 실행은 fast 가 아니라 검사 회피이며, PASS 로 기록할 수 없다. 이 스킬의 실제 호출 프로필은 외부 공개 프로덕션 (신청 페이지 Vercel 배포 등)이다 — 외부 독자는 토큰 비용이 아니라 마감을 본다. 그래서 전수가 기본값이다.

§2 — 실행 절차

정본 규칙: references/render-qa.md [[render-qa]] (4계층의 판정 기준·위반 조건·존재 이유 전부). 실행 하네스: scripts/render-qa-harness.js (RQ1 / RQ2·RQ2ALL / RQOBS·RQOBSALL).

  1. 계약 수취 — 호출 계약(처방문 § Render QA 인수인계)에서 페이지별 파라미터를 받는다: SCRIM 표 (씬 클래스별 c/a/op/mul/blur) + DECLARED_WIDTH_TOKENS (G1 폭 토큰 수) + 씬 테이블 (--raw-pos-m 선언 수 대조용) + RQ2-OBS 면제 선언 여부. 계약이 이를 동봉하지 않았으면 CSS 에서 재구성하되, 재구성했다는 사실과 재구성 값을 보고서에 기록한다 (F39 — 표 비동기는 "수리가 안 먹혔다" 오독을 만든다).
  2. 하네스 주입 — 프리뷰 콘솔/javascript_tool 에 하네스 로드, SCRIM 표·폭 토큰 수를 페이지 값으로 교체. 트랜지션 동결은 하네스가 수행(freezeMotion).
  3. 계층 순서대로 — 싼 검사가 먼저: RQ1(폭·스킴 순회) → RQ2ALL → RQOBSALL → RQ3(캡처 순회 + 매트릭스 기록). 각 계층의 위반 조건과 한계는 [[render-qa]] 가 정본이다.
  4. 판정 — 위반 = REVISE. 수리는 호출자가 하고, 이 스킬은 해당 계층부터 재검사한다 (≤2 루프 권장; 3루프 초과는 검사가 아니라 처방·배치의 결함 신호 — 호출자의 Step 5 로 회귀하라고 반환).

Read the full file on GitHub · 158 lines

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. 6d ago First seen · 158 lines · 221 tokens per session scan A 2e3970b6b615

Subscribe to this mod's changes

render-audit is a skill published in the GitHub repository laguna821/Achmage-Skills (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 221 tokens to every session and 2,595 once invoked, about $0.0011 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 2026-08-31.

Related

Other skills, from other repositories

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

run-integration-tests

Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.

dotnet/maui · 35 tokens

cli-e2e-testcase-writer

Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.

larksuite/cli · 78 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

every-app/open-seo · 35 tokens

agent-device-evidence

Records iOS/Android native MP4 evidence for test/repro flows extracted from an Expensify GitHub PR or issue. Use when the user asks to "record the flow for PR.

Expensify/App · 43 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens