Add a hook that warns before Claude Code burns your usage window
After using up his whole usage window in minutes several times, he built a Claude Code hook that checks before each send whether the cache has expired and the context is large, suggests compacting first, and blocks new subagents above 80% usage.
Source
zzyyxx332211 on Hacker News · 2026-10-22
Written in our own words. Credit to the original author. Link checked 2026-10-23.
What they did
After using up his whole usage window in minutes several times, he built a Claude Code hook that checks before each send whether the cache has expired and the context is large, suggests compacting first, and blocks new subagents above 80% usage.
Result (as claimed)
He's run it for 75 days and stays in control of his limits.
Tools they used
Cost: Claude Code: from $17/mo.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Add a hook that warns before Claude Code burns your usage window What the original author did: After using up his whole usage window in minutes several times, he built a Claude Code hook that checks before each send whether the cache has expired and the context is large, suggests compacting first, and blocks new subagents above 80% usage. Reported result (as claimed by the author): He's run it for 75 days and stays in control of his limits. Source: https://news.ycombinator.com/item?id=50199109 Tools they used: Claude Code Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Add a hook that warns before Claude Code burns your usage window What the original author did: After using up his whole usage window in minutes several times, he built a Claude Code hook that checks before each send whether the cache has expired and the context is large, suggests compacting first, and blocks new subagents above 80% usage. Reported result (as claimed by the author): He's run it for 75 days and stays in control of his limits. Source: https://news.ycombinator.com/item?id=50199109 Tools they used: Claude Code Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Add a hook that warns before Claude Code burns your usage window What the original author did: After using up his whole usage window in minutes several times, he built a Claude Code hook that checks before each send whether the cache has expired and the context is large, suggests compacting first, and blocks new subagents above 80% usage. Reported result (as claimed by the author): He's run it for 75 days and stays in control of his limits. Source: https://news.ycombinator.com/item?id=50199109 Tools they used: Claude Code Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to cut AI coding agent costs and token use · How to vibe code an app with Claude Code · How to run multiple coding agents together
Related use cases
Add architecture-aware Claude Code plugins for Flutter apps
A mobile developer built open-source Claude Code plugins for Flutter: one generates code that follows the app's architecture using the Dart MCP server and the language server, and review agents catch architecture violations before code ships.
Record architecture decisions from Claude Code as markdown in your repo
After making 14 architecture decisions and rejecting 15 alternatives in 3 days, a developer built datlas: say "record this" in Claude Code and the decision and its reasoning land in the repo as a markdown file.
Protect your Claude Code usage window with a guard mod
agent-usage-guard is an open-source Claude Code mod that watches usage and stops runaway sessions from burning your limit window.
Have Claude Code build an agent sandbox that injects credentials through a sidecar
He wanted a container sandbox for agents, so the harness runs on an internal-only network while a sidecar container injects credentials as a proxy. Claude Code built it quickly, with HTTPS and SSH working.