A skill for coding agents that runs a structured, multi-phase security audit of a codebase. It uses separate agents to find, challenge and verify vulnerabilities, then writes the results as machine-readable records and readable reports.
tokensaver
by Brucee
A plugin for Claude Code and Codex CLI that combines file search, batch editing and database queries into single tool calls, so the AI assistant uses fewer round-trips. It also tracks the calls saved, offers a multi-angle code review and can search past session history.
Proof level: ReadNew and promisingMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Requires an existing Claude Code or Codex CLI setup.
Things to check
- Requires an existing Claude Code or Codex CLI setup
- Makes a daily update check to GitHub (can be disabled)
- Relatively new project with a modest following
Can you use tokensaver commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with tokensaver?
- Search files, content and symbols in one call instead of several separate commands
- Apply batch edits across multiple files with fuzzy matching and syntax checks
- Run a multi-lens code review of your changes before pushing
How do you get tokensaver running?
Install it with two plugin commands inside Claude Code (or two terminal commands for Codex CLI); npm dependencies download automatically on first load.
Follow the official instructions in the project README.
Ways a business could use it
- Reduce AI coding assistant usage costs by cutting the number of tool calls per task
- Get a structured automated review of code changes before shipping client work
Who's talking about it
Checked 11 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in Agent skills and plugins
A skill for Claude Code and Codex that reviews a screen built with AI tools, finds the generic "AI look" such as purple gradients, glows and uneven spacing, and fixes it step by step. It is for making dashboards, apps and landing pages look designed rather than auto-generated.
A small collection of agent skills, each a folder with a SKILL.md file of instructions for an AI agent. At present it holds one skill, a Socratic tutor that teaches a topic through questions, a skill map and spaced review.