Nobody has claimed this office yet. Tablif records every new product and gives it an office; when its owner claims it, the lights go on.

What Tablif read on agent-usage-guard's site

agent-usage-guard describes itself as: “GitHub - rbartoli/agent-usage-guard: A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts agents across every session, and asks in Claude Code's own dialog. · GitHub”

Stage: Live, no waitlist

What it is

Calls itself “mod”.

Calls itself: mod

“A Claude Code mod”

Where it puts itself

Rules out “network requests”.

Says it will not: network requests

“It makes no network requests and starts no processes.”

How it runs

A command-line tool. Runs locally and works offline. Open source. AI is the core of the product.

Kind: cli
Runs where: on the device, offline
Open source: yes
AI role: core to the product

“Run these commands inside Claude Code v2.1.287 or later: /plugin marketplace add rbartoli/agent-usage-guard /plugin install agent-usage-guard@agent-usage-guard”

“Local and privacy-minimal. No network, no processes.”

What it works with

Names Claude Code and GitHub Copilot on its pages.

Names: Claude Code · GitHub Copilot

“Stop Claude Code from spending your usage window in minutes”

“GitHub Copilot Write better code with AI”

What it offers as proof

Live, no waitlist. Claims “394 subagent calls”. Publishes docs.

Number claimed: 394 subagent calls

“You must be signed in to star a repository”

“It spawned 394 subagent calls, 341 of them running at once, and pushed 84M context tokens through the API in ten minutes.”

Sources

Tablif read these pages, last on 23 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.

github.com/rbartoli/agent-usage-guard

agent-usage-guard · Office #49,214