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 jxsuite/jx --skill verifygit clone --depth 1 https://github.com/jxsuite/jxWrote 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/jxsuite/jx/verify)<a href="https://agentmods.dev/skills/jxsuite/jx/verify"><img src="https://agentmods.dev/badge/skills/jxsuite/jx/verify/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/jxsuite/jx/verify"><img src="https://agentmods.dev/badge/skills/jxsuite/jx/verify.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00028 | $0.00463 |
| Opus 5.5 | $0.00011 | $0.00185 |
| Sonnet 5.5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
verify scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Dev server: `bun run dev` at the repo root serves on port 3000 (often already running; its watcher rebuilds the parent studio bundle on save). Check with `curl -s -o /dev/null -w "%{http_code}" http://localhost:3000/p What it actually says
Verifying studio changes in a real browser
- Dev server:
bun run devat the repo root serves on port 3000 (often already running; its watcher rebuilds the parent studio bundle on save). Check withcurl -s -o /dev/null -w "%{http_code}" http://localhost:3000/packages/studio/index.html. Canvas-side changes (src/canvas/*) additionally needbun run buildin packages/studio — the iframe bundle is prebuilt and NOT watched. - Open
http://localhost:3000/packages/studio/index.htmlvia the Chrome DevTools MCP (mcp__chrome-devtools-nixos__*), then seed and enter a project:localStorage.setItem("jx-studio-recent-projects", JSON.stringify([{ name: "examples", root: "examples", timestamp: <ms> }])), reload.- Click the "Recent projects" toolbar button → the "examples" menu item.
- The left file tree is plain DOM (
.file-tree-itemwith.file-tree-name), but it is NOT exposed in the a11y snapshot — find/click nodes viaevaluate_script. Quick Open (⌘P button) types-then-Enter is flaky under MCP; prefer the tree. - The editor tab strip is
.tab-strip(child of#tab-strip), tabs are.tab-strip-tabwith.tab-strip-label. It is theoverflow-x: autoscroll container; read/writescrollLeftdirectly. - Synthetic events via
evaluate_script(new WheelEvent(...),el.click()) exercise the real lit handlers — the app does not checkisTrusted. Note an app-level ancestor handler callspreventDefault()on ctrl+wheel (zoom), so test per-element handlers withbubbles: falsewhen isolating. - Default MCP viewport is 780px wide;
resize_pageto ~1400px for readable screenshots and to keep CDP clicks from missing off-viewport targets.
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.
- 11d ago First seen · 16 lines · 28 tokens per session scan A ab6b3b3484d8
verify is a skill published in the GitHub repository jxsuite/jx (7 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 463 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
writing-playwright-tests
Provides patterns for writing maintainable E2E test scripts with Playwright, focusing on selector strategies, page objects, and wait handling for legacy application retrofitting.
ensemble-playwright-test
Automated E2E testing and error resolution using Playwright MCP integration (Codex skill for /ensemble:playwright-test).
Browser Use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
web-validation
Comprehensive web page validation with authentication, screenshot capture, mobile testing, and enhanced error detection.
playwright-cli-helpers
Default verification tool for local HTML files. Use visual-check.sh as the FIRST choice whenever you need to verify, test, or check any local HTML page — whether confirming elements render correctly, checking layout, detecting overflow, or asserting uniform widths. Prefer this over raw playwright-cli commands. Also…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.