ai-core/locks

A coordination system for making sure only one application instance runs a critical piece of work at a time. It is separate from chat-data storage, which saves durable conversation state.

In plain words
What is it for?
Use it to coordinate concurrent AI chat work, optionally alongside chat persistence, with either in-memory or distributed locks.
Why use it?
It prevents multiple servers or processes from changing the same work at once and causing race conditions.

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

Made for: Claude Code, Codex.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,178 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 $0.00112 $0.01178
Opus 5 $0.00056 $0.00589
Sonnet 5 $0.00022 $0.00236
Haiku 4.5 $0.00011 $0.00118

Measured 2d ago against content hash a825b51e182c, 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/locks 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/locks/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Locks (coordination — not persistence)

Dependency note: This skill builds on ai-core and ai-core/middleware. withLocks is a ChatMiddleware that provides a capability. Locks are not part of AIPersistence.stores and are not composed with composePersistence — they ship in @tanstack/ai, independent of @tanstack/ai-persistence.

Why separate?

State stores answer "what is durable chat data?"
Locks answer "who may run this critical section right now?"

withPersistence does not automatically lock a whole turn. Take a per-thread (or other) lock yourself when multi-writer races matter.

Wire locks

import { withLocks, InMemoryLockStore } from '@tanstack/ai/locks'

middleware: [
  withLocks(new InMemoryLockStore()), // single process
]

Alongside persistence — optional, locks do not require it:

import { withLocks, InMemoryLockStore } from '@tanstack/ai/locks'
import { withPersistence } from '@tanstack/ai-persistence'

middleware: [withPersistence(persistence), withLocks(new InMemoryLockStore())]

withLocks provides LocksCapability for downstream middleware (e.g. sandbox). Order: usually state first, locks alongside or after depending on who consumes the capability.

The contract

interface LockStore {
  withLock<T>(key: string, fn: (signal: AbortSignal) => Promise<T>): Promise<T>
}

InMemoryLockStore ships in @tanstack/ai/locks: a per-key promise chain, correct within a single process only. Multi-instance deployments need a distributed implementation — you write it. The Cloudflare Durable Object recipe is in ai-persistence/build-cloudflare-adapter (@tanstack/ai-persistence).

Type your own store with defineLock (autocomplete, no : LockStore annotation), then hand it to withLocks. Acquire the key, run fn, release when fn settles:

import { defineLock, withLocks } from '@tanstack/ai/locks'
import { acquire } from './my-lock-backend'

const locks = defineLock({
  async withLock(key, fn) {
    const { release, signal } = await acquire(key)
    try {
      return await fn(signal)
    } finally {
      release()
    }
  },
})

middleware: [withLocks(locks)]

Read the full file on GitHub · 144 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. 2d ago First seen · 144 lines · 112 tokens per session scan A a825b51e182c

Subscribe to this mod's changes

ai-core/locks is a skill published in the GitHub repository TanStack/ai (3,045 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 1,178 once invoked, about $0.0006 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.