Filter CLI context to cut LLM tokens before the prompt

Built Lowfat, a pluggable CLI filter the author says saved 91.8% of their LLM tokens.

Free tier30 minBeginnerSource linked

Source

zdkaster on Hacker News · 2026-06-05 · Project link

Written in our own words. Credit to the original author. Link checked 2026-10-15.

What they did

Built Lowfat, a pluggable CLI filter the author says saved 91.8% of their LLM tokens.

Result (as claimed)

Author claims 91.8% token savings.

Tools they used

Claude Code OpenAI Codex

Cost: Claude Code: free plan, paid from $17/mo; OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.

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, OpenAI Codex. 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: Filter CLI context to cut LLM tokens before the prompt
What the original author did: Built Lowfat, a pluggable CLI filter the author says saved 91.8% of their LLM tokens.
Reported result (as claimed by the author): Author claims 91.8% token savings.
Source: https://news.ycombinator.com/item?id=48409955
Tools they used: Claude Code, OpenAI Codex
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: Filter CLI context to cut LLM tokens before the prompt
What the original author did: Built Lowfat, a pluggable CLI filter the author says saved 91.8% of their LLM tokens.
Reported result (as claimed by the author): Author claims 91.8% token savings.
Source: https://news.ycombinator.com/item?id=48409955
Tools they used: Claude Code, OpenAI Codex
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: Filter CLI context to cut LLM tokens before the prompt
What the original author did: Built Lowfat, a pluggable CLI filter the author says saved 91.8% of their LLM tokens.
Reported result (as claimed by the author): Author claims 91.8% token savings.
Source: https://news.ycombinator.com/item?id=48409955
Tools they used: Claude Code, OpenAI Codex
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