Skip to content
Back to search

token-budget-guard-lite

Local-first Python & PowerShell utilities to cut AI agent DOM/context token bloat by 40-60% and enforce a 2-strike circuit breaker.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/truongminhphu315a-droid--token-budget-guard-lite/badge.svg)](/listings/truongminhphu315a-droid--token-budget-guard-lite)

HTML

<a href="/listings/truongminhphu315a-droid--token-budget-guard-lite"><img src="/api/listings/truongminhphu315a-droid--token-budget-guard-lite/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

# Clone the repo
git clone https://github.com/truongminhphu315a-droid/token-budget-guard-lite.git
cd token-budget-guard-lite

# Run the benchmark (requires PowerShell 5+)
.\\Benchmark_Token_Cost.ps1

# Or run the Python payload
python compact_payload.py

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 27 lines
  1. # token-budget-guard-lite
  2. Open‑source utilities to help you stay within a token budget when running local LLMs. This repo contains a minimal, fully‑functional PowerShell benchmark, a compact Python payload, and a small example dump.
  3. ## Features
  4. - **Benchmark_Token_Cost.ps1** – measures token‑budget impact on inference cost.
  5. - **compact_payload.py** – tiny script that demonstrates a low‑overhead prompt with a token limit.
  6. - **examples/raw_dom_dump.txt** – sample output you can pipe into the scripts for a quick 30‑second test.
  7. ## Quick Start
  8. ```powershell
  9. # Clone the repo
  10. git clone https://github.com/truongminhphu315a-droid/token-budget-guard-lite.git
  11. cd token-budget-guard-lite
  12. # Run the benchmark (requires PowerShell 5+)
  13. .\\Benchmark_Token_Cost.ps1
  14. # Or run the Python payload
  15. python compact_payload.py
  16. ```
  17. ## License
  18. MIT – see the LICENSE file.
  19. ## Roadmap & Community Requests
  20. We welcome contributions and ideas. Open an Issue or Discussion if you’d like new features, integrations, or have feedback on improving token‑budget management.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.