What is ai-core/middleware?

Middleware hooks for observing and changing stages of an AI chat request, such as startup, streamed chunks, tool calls, usage, completion, abortion, and errors. Middleware is code that runs between an application and the chat process.

Adding analytics, logging, tracing, tool caching, error reporting, and configuration changes to chats built with the referenced AI chat library.

Applications often need one place to log chats, track usage, report errors, cache tool results, or inspect streamed responses. These hooks provide lifecycle points for adding that behavior.

ai-core/middleware — Skill by TanStack

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/ai/middleware

Any agent

npx skills add TanStack/ai --skill middleware

Clone the repo

git clone --depth 1 https://github.com/TanStack/ai

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,010 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.

Model	Per session	Once invoked
Fable 5	$0.00086	$0.08010
Opus 5	$0.00043	$0.04005
Sonnet 5	$0.00017	$0.01602
Haiku 4.5	$0.00009	$0.00801

Measured 2d ago against content hash 13d23d966f6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-core/middleware 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.

packages/ai/skills/ai-core/middleware/SKILL.md · 794 lines

How it starts

The opening of the file, as written. The whole thing — 794 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Middleware

Dependency note: This skill builds on ai-core. Read it first for critical rules.

Setup — Analytics Tracking Middleware

import { chat, toServerSentEventsResponse } from '@tanstack/ai'
import { openaiText } from '@tanstack/ai-openai'

const stream = chat({
  adapter: openaiText('gpt-5.2'),
  messages,
  middleware: [
    {
      onStart: (ctx) => {
        console.log('Chat started:', ctx.model)
      },
      onFinish: (ctx, info) => {
        trackAnalytics({ model: ctx.model, tokens: info.usage?.totalTokens })
      },
      onError: (ctx, info) => {
        reportError(info.error)
      },
    },
  ],
})

return toServerSentEventsResponse(stream)

Hooks Reference

Every hook receives a ChatMiddlewareContext as its first argument, which provides requestId, streamId, phase, iteration, chunkIndex, model, provider, signal, abort(), defer(), and more.

Hook	When	Second Argument
`onConfig`	Once at startup (`init`) + once per iteration (`beforeModel`) + once at a separate-finalization boundary	`ChatMiddlewareConfig` (return partial to merge)
`onStructuredOutputConfig`	Once at the separate-finalization boundary	`StructuredOutputMiddlewareConfig` (return partial)
`onStart`	Once after initial `onConfig`	none
`onIteration`	Start of each agent loop iteration	`IterationInfo`
`onShouldContinue`	Whether to start another agent-loop iteration (AND with strategy; `false` stops)	`AgentLoopState`
`onChunk`	Every streamed chunk	`StreamChunk` (return void/chunk/chunk[]/null)
`onBeforeToolCall`	Before each tool executes	`ToolCallHookContext` (return decision or void)
`onAfterToolCall`	After each tool executes	`AfterToolCallInfo`
`onToolPhaseComplete`	After all tool calls in an iteration	`ToolPhaseCompleteInfo`
`onUsage`	When `RUN_FINISHED` includes usage data	`UsageInfo`
`onFinish`	Run completed normally	`FinishInfo`
`onAbort`	Run was aborted	`AbortInfo`
`onError`	Unhandled error occurred	`ErrorInfo`

Read the full file on GitHub · 794 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.

2d ago First seen · 794 lines · 86 tokens per session scan A 13d23d966f6a

Subscribe to this mod's changes

ai-core/middleware is a skill published in the GitHub repository TanStack/ai (3,045 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 8,010 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.

Analytics and metrics Data and AI ai ai-agents ai-sdk anthropic chatbot function-calling

ai-core/middleware

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Middleware

Setup — Analytics Tracking Middleware

Hooks Reference

What this file has done since we first saw it

Other skills, from other repositories

keybindings-help

options

tmux

summarize

github

workflow-authoring