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/tanstack/devtools/devtools-plugin-panelnpx skills add TanStack/devtools --skill devtools-plugin-panelgit clone --depth 1 https://github.com/TanStack/devtoolsWhat 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 | $0.00084 | $0.02911 |
| Opus 5 | $0.00042 | $0.01456 |
| Sonnet 5 | $0.00017 | $0.00582 |
| Haiku 4.5 | $0.00008 | $0.00291 |
Grade A, and why
devtools-plugin-panel 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 yesterday.
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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TanStackDevtoolsPlugin Interface
The low-level contract every plugin implements. Framework adapters wrap this automatically.
// Source: packages/devtools/src/context/devtools-context.tsx
interface TanStackDevtoolsPlugin {
id?: string
name: string | ((el: HTMLHeadingElement, theme: 'dark' | 'light') => void)
render: (el: HTMLDivElement, theme: 'dark' | 'light') => void
destroy?: (pluginId: string) => void
defaultOpen?: boolean
}
name(required) -- String tab title, or function receiving(el, theme)for custom rendering.render(required) -- Called on activation with a<div>container and theme. Called again on theme change.id(optional) -- Stable identifier. If omitted:name.toLowerCase().replace(' ', '-')-{index}. Explicit ids persist selection across reloads.defaultOpen(optional) -- Opens panel on first load when no saved state. Max 3 open. Does not override saved preferences.destroy(optional) -- Called on deactivation or unmount. Framework adapters handle cleanup automatically.
Two Development Paths
Path 1: Solid.js Core + Framework Adapters (Multi-Framework)
Build the panel in Solid.js using @tanstack/devtools-ui components. Use constructCoreClass for lazy loading, then createReactPanel/createSolidPanel to wrap for each framework. The devtools core is Solid, so Solid panels run natively.
Path 2: Framework-Specific Panel (Single Framework)
Build directly in your framework and use createReactPlugin/createVuePlugin/createSolidPlugin/createPreactPlugin from @tanstack/devtools-utils.
Path 1: Solid.js Core Panel
Step 1: Define Event Map and Create EventClient
// src/event-client.ts
import { EventClient } from '@tanstack/devtools-event-client'
type StoreEvents = {
'state-changed': { storeName: string; state: unknown; timestamp: number }
'action-dispatched': { storeName: string; action: string; payload: unknown }
reset: void
}
class StoreInspectorClient extends EventClient<StoreEvents> {
constructor() {
super({ pluginId: 'store-inspector' })
}
}
export const storeInspector = new StoreInspectorClient()
What ships with it
1 file 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.
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.
- yesterday First seen · 430 lines · 84 tokens per session scan A fc8e3d0cb0c5
devtools-plugin-panel is a skill published in the GitHub repository TanStack/devtools (493 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 2,911 once invoked, about $0.0004 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.
Other skills, from other repositories
install-next
Installs and wires @rsc-boundary/next into a Next.js App Router app (dependencies, root layout provider, optional explicit markers). Use when the user wants to add RSC Boundary, integrate @rsc-boundary/next, or set up server/client boundary devtools in Next.js. The unscoped rsc-boundary package on npm is deprecated …
install-start
Installs and wires the npm package @rsc-boundary/start into a TanStack Start app (dependencies, root route provider, optional explicit markers). Use when the user wants to add RSC Boundary to a TanStack Start / TanStack Router app, or set up server/client boundary devtools with TanStack.
dev-inspector
Use this skill when the user wants to add DevInspector (dev-inspector-mcp) to their project, integrate MCP for their editor, set up ACP agents, click-to-source in browser, or debug "inspector not showing" / "MCP not connecting" issues. Triggers on phrases like "add dev inspector", "click to component", "setup…
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
auth-security
Secure authentication and authorization when credentials, sessions, roles, or permissions change.
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.