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-framework-adaptersnpx skills add TanStack/devtools --skill devtools-framework-adaptersgit 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 | $0.02204 |
| Opus 5 | $0.00042 | $0.01102 |
| Sonnet 5 | $0.00017 | $0.00441 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
devtools-framework-adapters 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.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use @tanstack/devtools-utils factory functions to create per-framework devtools plugin adapters. Each framework has a subpath export (/react, /vue, /solid, /preact) with two factories:
createXPlugin-- wraps a component into a[Plugin, NoOpPlugin]tuple for tree-shaking.createXPanel-- wraps a class-based devtools core (mount/unmount) into a[Panel, NoOpPanel]component tuple.
Key Source Files
packages/devtools-utils/src/react/plugin.tsx-- createReactPluginpackages/devtools-utils/src/react/panel.tsx-- createReactPanel, DevtoolsPanelPropspackages/devtools-utils/src/vue/plugin.ts-- createVuePlugin (different API)packages/devtools-utils/src/vue/panel.ts-- createVuePanel, DevtoolsPanelProps (includes 'system' theme)packages/devtools-utils/src/solid/plugin.tsx-- createSolidPluginpackages/devtools-utils/src/solid/panel.tsx-- createSolidPanelpackages/devtools-utils/src/solid/class.ts-- constructCoreClass (Solid-specific)packages/devtools-utils/src/preact/plugin.tsx-- createPreactPluginpackages/devtools-utils/src/preact/panel.tsx-- createPreactPanel
Shared Pattern
All four frameworks follow the same two-factory pattern:
Plugin Factory
Every createXPlugin returns readonly [Plugin, NoOpPlugin]:
- Plugin -- returns a plugin object with metadata and a
renderfunction that renders your component. - NoOpPlugin -- returns a plugin object with the same metadata but renders an empty fragment.
Panel Factory
Every createXPanel returns readonly [Panel, NoOpPanel]:
- Panel -- a framework component that creates a
<div style="height:100%">, instantiates the core class, callscore.mount(el, theme)on mount, andcore.unmount()on cleanup. - NoOpPanel -- renders an empty fragment.
DevtoolsPanelProps
// React, Solid, Preact
interface DevtoolsPanelProps {
theme?: 'light' | 'dark'
}
// Vue (note: includes 'system')
interface DevtoolsPanelProps {
theme?: 'dark' | 'light' | 'system'
}
What ships with it
4 files 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.
- 2d ago First seen · 264 lines · 84 tokens per session scan A e0d3e0ca5cbb
devtools-framework-adapters 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 2,204 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.