devtools-instrumentation

A guide for adding carefully chosen diagnostic events to a software library. These events report important points such as middleware, state changes, lifecycle stages and errors to developer tools.

In plain words
What is it for?
Use it to identify useful instrumentation points, add shared event fields, reduce duplicate events and protect production code from unnecessary reporting.
Why use it?
It makes internal behaviour easier to inspect while limiting noisy or repetitive event data.

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/tanstack/devtools/devtools-instrumentation
Any agent
npx skills add TanStack/devtools --skill devtools-instrumentation
Clone the repo
git clone --depth 1 https://github.com/TanStack/devtools

Made for: Claude Code, Codex.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,840 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 $0.00064 $0.02840
Opus 5 $0.00032 $0.01420
Sonnet 5 $0.00013 $0.00568
Haiku 4.5 $0.00006 $0.00284

Measured yesterday against content hash 0a01c2c54e6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devtools-instrumentation 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.

packages/event-bus-client/skills/devtools-instrumentation/SKILL.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

devtools-instrumentation

Prerequisite: Read the devtools-event-client skill first for EventClient creation, event maps, and emit()/on() API.

Strategic placement of emit() calls inside a library to send high-value diagnostic data to TanStack Devtools panels. Maximum insight with minimum noise.

Key Insight

The event bus transparently bridges server/client and cross-tab boundaries. emit() on the server arrives on the client via WebSocket/SSE. emit() in one tab reaches other tabs via BroadcastChannel. No transport code needed -- just emit at the right place.

For prototyping, throw in many events. For production, consolidate down to the fewest events that carry the most information.

Where to Instrument

Emit at architecture boundaries, not inside implementation details:

  1. Middleware/interceptor entry and exit -- wrap the chain, not each middleware
  2. State transitions -- when state moves between logical phases (idle -> loading -> success/error)
  3. Lifecycle hooks -- mount, unmount, connect, disconnect, ready
  4. Error boundaries -- caught exceptions, retries, fallbacks
  5. User-initiated actions processed -- after fully applied, not before

Do NOT emit from: internal utility functions, loop iterations, getter/setter accesses, intermediate computation steps.

Core Patterns

1. Middleware/Interceptor Instrumentation

Wrap the pipeline at the boundary, not each middleware individually.

import { EventClient } from '@tanstack/devtools-event-client'

type RouterEvents = {
  'request-processed': {
    id: string
    method: string
    path: string
    duration: number
    middlewareChain: Array<{ name: string; durationMs: number }>
    status: number
    error?: string
  }
}

class RouterDevtoolsClient extends EventClient<RouterEvents> {
  constructor() {
    super({
      pluginId: 'my-router',
      enabled: process.env.NODE_ENV !== 'production',
    })
  }
}

export const routerDevtools = new RouterDevtoolsClient()

Read the full file on GitHub · 424 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. yesterday First seen · 424 lines · 64 tokens per session scan A 0a01c2c54e6d

Subscribe to this mod's changes

devtools-instrumentation is a skill published in the GitHub repository TanStack/devtools (493 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 2,840 once invoked, about $0.0003 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

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 …

foxted/rsc-boundary · 82 tokens

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.

foxted/rsc-boundary · 66 tokens

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…

mcpc-tech/dev-inspector-mcp · 97 tokens

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.

KbWen/agent-virtual-office · 50 tokens

auth-security

Secure authentication and authorization when credentials, sessions, roles, or permissions change.

KbWen/agent-virtual-office · 18 tokens

karpathy-principles

Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.

KbWen/agent-virtual-office · 34 tokens