verify

A runtime testing method for changes to AgentTools, including their real tool calls and browser-based result displays.

In plain words
What is it for?
Use it to run AgentTools through the MCP pipeline, verify Wolfram Language tools, and inspect MCP Apps viewers in a browser.
Why use it?
It checks what users actually experience instead of relying only on code inspection, including whether tools and their visual results work together.

Skill for Claude CodeCodex

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/wolframresearch/agenttools/verify
Any agent
npx skills add WolframResearch/AgentTools --skill verify
Clone the repo
git clone --depth 1 https://github.com/WolframResearch/AgentTools

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 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 $0.00030 $0.00761
Opus 5 $0.00015 $0.00380
Sonnet 5 $0.00006 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 2d ago against content hash fc7f3dd90cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify 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 2d 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/verify/SKILL.md · 23 lines

How it starts

The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifying AgentTools changes at runtime

Wolfram Language side (tools, server, UI results)

  • Always set WOLFRAMSCRIPT_KERNELPATH="C:/Program Files/Wolfram Research/Wolfram/15.0/wolfram.exe" (or newer). Plain wolframscript may pick an older kernel; AgentTools requires 15.0+, and under an older kernel PacletDirectoryLoad + Get["Wolfram`AgentTools`"] silently falls back to the installed Repository paclet — you exercise the wrong code. Confirm with FindFile["Wolfram`AgentTools`"] → must resolve under the dev directory.
  • Load the dev paclet: PacletDirectoryLoad["H:\\Documents\\AgentTools"]; Get["Wolfram`AgentTools`"].
  • To drive a tool exactly as the MCP server dispatches it, call its registered "Function" (see $defaultMCPTools[name] in Kernel/Tools/*.wl) with the parsed-args association, e.g. Wolfram`AgentTools`Tools`WolframLanguageEvaluator`Private`evaluateWolframLanguage[<|"code" -> ...|>].
  • To trigger the MCP Apps UI path (cloud-deployed notebook + _meta.notebookUrl), first set Wolfram`AgentTools`Common`$clientSupportsUI = True and be cloud-connected. Export the result with Developer`WriteRawJSONFile — it is the exact content/_meta payload a host forwards to a viewer.
  • For an A/B against pre-change behavior, git worktree add <scratch>/head-copy HEAD and point PacletDirectoryLoad at the worktree in a second wolframscript run. Use a different input (the deploy target is content-hashed, same input overwrites the same cloud object). Remove the worktree afterwards.

MCP Apps viewers (Assets/Apps/*.html)

  • All viewers speak the same iframe protocol: they send ui/initialize (reply with {protocolVersion, hostInfo, hostContext}), then notify ui/notifications/initialized; after that, post {jsonrpc:"2.0", method:"ui/notifications/tool-result", params:{content, _meta}} into the iframe.
  • Harness that works: a host.html that iframes the viewer and plays the host role over postMessage + a no-dep node static server + Playwright (npm i playwright locally; chromium via npx playwright install chromium). Set colorScheme: "dark" on the browser context to reproduce dark-host bugs; the embed needs real network (unpkg CDN + wolframcloud.com) and takes 10–60 s.
  • The notebook embedder (useShadowDOM: true) attaches an open shadow root to a wrapper <div> it creates inside the container, not to the container itself. Wait for embed completion by recursively searching open shadow roots for expected notebook text; read computed styles with getComputedStyle on shadow-tree elements.
  • Playwright frame-picking gotcha: the host page URL carries the viewer filename in its query string, so match f !== page.mainFrame() when locating the viewer frame.
  • Verified evidence to capture: computed color of shadow text leaves (dark-theme leak shows as rgb(224, 224, 224)), computed font-family, and full-page screenshots.

Read the full file on GitHub · 23 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. 2d ago First seen · 23 lines · 30 tokens per session scan A fc7f3dd90cf6

Subscribe to this mod's changes

verify is a skill published in the GitHub repository WolframResearch/AgentTools (82 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 761 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 2026-08-30.

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

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

traceway-setup

Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…

tracewayapp/traceway · 134 tokens

make-resume

中文可编辑简历制作技能:根据用户经历选择或复刻模板,生成可编辑 HTML 简历并提供 PDF 导出;当用户输入“/make-resume”或要求制作、修改、复刻简历文件时使用。.

Hisn00w/ASu-skills · 56 tokens