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 TanStack/devtools --skill devtools-webmcpgit clone --depth 1 https://github.com/TanStack/devtoolsWrote 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/tanstack/devtools/devtools-webmcp)<a href="https://agentmods.dev/skills/tanstack/devtools/devtools-webmcp"><img src="https://agentmods.dev/badge/skills/tanstack/devtools/devtools-webmcp/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/tanstack/devtools/devtools-webmcp"><img src="https://agentmods.dev/badge/skills/tanstack/devtools/devtools-webmcp.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 | $0.00043 | $0.01608 |
| Opus 5.5 | $0.00017 | $0.00643 |
| Sonnet 5.5 | $0.00009 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
devtools-webmcp 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 23d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devtools-webmcp
An agent in the browser cannot see the internals of your library. WebMCP tools give that agent a way to read those internals during development.
The package is @tanstack/devtools-webmcp. It has no runtime dependencies. These tools do not appear in a devtools panel.
Register
Paste this call into the library.
import { registerDevtoolsTools } from '@tanstack/devtools-webmcp'
const stop = registerDevtoolsTools({
pluginId: 'tanstack.query',
instanceId: 'main',
tools: [
{
name: 'getQueryCache',
description: 'Return a JSON summary of the query cache.',
inputSchema: {
type: 'object',
properties: {
queryHash: { type: 'string' },
},
},
execute: (input) => summarize(client, input),
},
],
})
stop()
summarize and client are your own library code. This sample does not define them.
If the tools must stay, do not call stop().
When the tools must leave the page, call stop().
The call returns stop at once. The call does not return the registerTool promise.
Names
pluginId is required. instanceId is optional.
An empty instanceId means the same thing as no instanceId. An empty instanceId is legal.
The browser tool name is pluginId.name. When instanceId is a non-empty string, the browser tool name is pluginId.instanceId.name.
In the sample, the browser tool name is tanstack.query.main.getQueryCache.
A part is pluginId or name. When instanceId is a non-empty string, that value is also a part.
Each part is a non-empty string. Each part uses only ASCII letters (A-Z and a-z), digits, _, -, and ..
The full tool name has 1 to 128 characters.
Tool fields
A tool needs name, description, and execute.
name: the last part of the browser tool name.description: the text that the agent reads.title: an optional string.inputSchema: an optional JSON Schema.execute: the function that returns the data.
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.
- 23d ago First seen · 195 lines · 43 tokens per session scan A dfb35a0094c2
devtools-webmcp is a skill published in the GitHub repository TanStack/devtools (506 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,608 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
next-dev-loop
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running next dev.
next-bundle-optimizer
Audit and reduce Next.js browser initial-load work. Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction.
next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…