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 agentmods add skills/seed-hypermedia/seed/testing-editor-harnessnpx skills add seed-hypermedia/seed --skill testing-editor-harnessgit clone --depth 1 https://github.com/seed-hypermedia/seedWrote 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/seed-hypermedia/seed/testing-editor-harness)<a href="https://agentmods.dev/skills/seed-hypermedia/seed/testing-editor-harness"><img src="https://agentmods.dev/badge/skills/seed-hypermedia/seed/testing-editor-harness.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00041 | $0.01629 |
| Opus 5 | $0.00020 | $0.00814 |
| Sonnet 5 | $0.00008 | $0.00326 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
testing-editor-harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing the editor E2E harness
Devin Secrets Needed
None.
Environment
- Work from
frontend/packages/editor. - Use Node 22.22.x and the pnpm fallback at
/home/ubuntu/.local/bin/pnpmifmise/corepack is rate-limited. - The harness uses Vite:
pnpm test:harnessrunsvite --config e2e/vite.config.tsonhttp://localhost:5180.
Running the harness
export PATH="/home/ubuntu/.local/bin:/home/ubuntu/.local/share/mise/installs/node/22.22.0/bin:$PATH"
cd /home/ubuntu/repos/seed/frontend/packages/editor
pnpm test:harness
Open the browser at a real-mode fixture URL, e.g.:
http://localhost:5180/?real=1&fixture=allBlocks&badges=1
real=1mounts the actualDocumentEditorwith a mock document machine.fixture=allBlocksrenders one of every block type defined ine2e/test-app/TestEditor.tsx.badges=1gives every fixture block a mock citation/comment count so supernumber badges render.
Mobile viewport emulation
The Chrome for Testing instance in this environment listens on remote-debugging port 29229. Use CDP to set a mobile viewport without keeping DevTools open:
// /tmp/set-mobile-viewport.js
const http = require('http');
const WebSocket = require('/home/ubuntu/repos/seed/node_modules/ws');
http.get('http://localhost:29229/json/list', (res) => {
let data = '';
res.on('data', (c) => (data += c));
res.on('end', () => {
const pages = JSON.parse(data);
const page = pages.find((p) => p.type === 'page' && (p.url.includes('localhost:5180') || p.url === 'about:blank'));
if (!page) { console.error('No suitable page found'); process.exit(1); }
const ws = new WebSocket(page.webSocketDebuggerUrl);
ws.on('open', () => {
ws.send(JSON.stringify({id: 1, method: 'Page.navigate', params: {url: 'http://localhost:5180/?real=1&fixture=allBlocks&badges=1'}}));
setTimeout(() => {
ws.send(JSON.stringify({id: 2, method: 'Emulation.setDeviceMetricsOverride', params: {
width: 390, height: 844, deviceScaleFactor: 2, mobile: true,
screenWidth: 390, screenHeight: 844,
}}));
ws.send(JSON.stringify({id: 3, method: 'Emulation.setTouchEmulationEnabled', params: {enabled: true}}));
setTimeout(() => ws.close(), 500);
}, 300);
});
});
});
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.
- 3d ago First seen · 121 lines · 41 tokens per session scan A bfa9f38403de
testing-editor-harness is a skill published in the GitHub repository seed-hypermedia/seed (56 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 1,629 once invoked, about $0.0002 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.
Other skills, from other repositories
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
accessibility-analysis
服務可達性分析工具箱(accessibility / service coverage)。當用戶說「30km 路網可達」「最近 X 站」「服務範圍」「沙漠」「孤島」「等時圈」「isochrone」「可達性分析」「路網覆蓋」或要新增任何「離 POI 多遠」類型的分析時觸發。整合 mini-taiwan-pulse + taipei-gis-analytics 兩端 SOP,覆蓋三種視覺模式(路網染色 / Polygon 沿路網 / Hex 格點)、三套既有 reference pipeline 對照、模式選擇決策樹、常見坑(Overpass mirror 不穩 / pyrosm 爆 RAM / multi-bucket /…
ui-design
UI 样式修改协作流程(已有界面的视觉层微调)。触发硬条件:页面已经在代码里跑着,改的只是它的视觉表现——布局、间距、颜色、字号、圆角、组件搭配。通过"读代码 + ASCII 画出现状让用户确认 → 给 2-3 个 ASCII 方案 → 用户选定 → 最小改动 → 微调"的流程,减少沟通偏差、避免浪费 token。产出:只动样式的代码 diff。硬边界:不动业务逻辑、不动数据流、不改交互行为、不顺手重构。不适用于:界面还不存在、要从零探索长什么样(用 design-exploration)、改的是功能或交互逻辑而不只是视觉(用 req-change-workflow)、照着设计图/截图复刻整页(用…