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-productionnpx skills add TanStack/devtools --skill devtools-productiongit 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 | $0.00043 | $0.03398 |
| Opus 5 | $0.00022 | $0.01699 |
| Sonnet 5 | $0.00009 | $0.00680 |
| Haiku 4.5 | $0.00004 | $0.00340 |
Grade A, and why
devtools-production 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 — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TanStack Devtools Production Handling
Prerequisite: Read the devtools-app-setup skill first. The initial setup decisions (framework adapter, Vite plugin, dependency type) directly determine which production strategy applies.
How Production Stripping Works
TanStack Devtools has two independent mechanisms for keeping devtools out of production bundles. Understanding both is essential because they serve different project types.
Mechanism 1: Vite Plugin Auto-Stripping (Vite projects)
The @tanstack/devtools-vite plugin includes a sub-plugin named @tanstack/devtools:remove-devtools-on-build. When removeDevtoolsOnBuild is true (the default), this plugin runs during vite build and any non-serve command where the mode is production.
It uses oxc-parser to parse every source file, find imports from these packages, and remove them along with any JSX elements they produce:
@tanstack/react-devtools@tanstack/preact-devtools@tanstack/solid-devtools@tanstack/vue-devtools@tanstack/svelte-devtools@tanstack/angular-devtools@tanstack/devtools
The stripping is AST-based. It removes the import declaration, then finds and removes any JSX elements whose tag name matches one of the imported identifiers. It also traces plugin references inside the plugins prop array and removes their imports if they become unused.
Source: packages/devtools-vite/src/remove-devtools.ts
This means for a standard Vite project, the default setup from devtools-app-setup already handles production correctly with zero additional configuration:
// This import and JSX element are completely removed from the production build
import { TanStackDevtools } from '@tanstack/react-devtools'
function App() {
return (
<>
<YourApp />
<TanStackDevtools
plugins={
[
/* ... */
]
}
/>
</>
)
}
Mechanism 2: Conditional Exports (package.json)
The @tanstack/devtools core package uses Node.js conditional exports to serve different bundles based on the environment:
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 · 463 lines · 43 tokens per session scan A 4ce57a776bff
devtools-production is a skill published in the GitHub repository TanStack/devtools (493 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 3,398 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.
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.