What is auto-polish?
auto-polish is a Claude Code mod by mako-code that every prompt you type gets a quiet second read: without changing your words, a hidden note gives Claude the goal in one line, the likely scope, the project's checks to keep green, and what. It is listed under Interface and has 2 GitHub stars.
| Type | Claude code mod |
|---|---|
| Author | mako-code |
| Repository | mako-code/gobworks |
| Popularity | 2 GitHub stars |
| Category | Interface |
| Security | Review before installing (68/100) |
| Rank | #1,245 of 5,272 Claude Code mods; #482 in Interface |
| License | MIT |
| Last commit | 2026-10-04 |
| Hooks | 7 events |
| Sees | every prompt, every tool call |
| Draws on | AbovePrompt |
Is auto-polish safe to install?
auto-polish scores 68/100 on the MCPMods security check: Review before installing. Things to review: starts processes outside the sandbox; watches every prompt or event. It passed 4 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| No network access | Pass |
| Starts processes outside the sandbox | Review |
| Writes no files or config | Pass |
| Doesn't read environment variables | Pass |
| Watches every prompt or event | Review |
| Drives Claude (model calls, prompts) | Note |
| Validator reported problems | Note |
| Has an open-source license | Pass |
API calls in its code
| Call | What it means |
|---|---|
$.clock.after | |
$.clock.now | |
$.clock.sleep | |
$.command.register | |
$.fs.list | reads files |
$.fs.read | reads files |
$.model.complete | drives Claude |
$.process.run | runs processes |
$.prompt.fill | writes the prompt box |
$.prompt.submit | drives Claude |
$.session.root | |
$.session.surfaces | |
$.state.get | |
$.state.set | |
$.ui.log | draws interface |
$.ui.resolve | draws interface |
$.ui.toast | draws interface |
How do I install auto-polish?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/mako-code/gobworks claude plugin validate ./gobworks/mods/autopilot/auto-polish
- Install it. Run this in your terminal, then /reload-plugins in an open session.
claude plugin marketplace add mako-code/gobworks && claude plugin install auto-polish@gobworks
Or ask Claude to set it up
Paste this into Claude Code and it installs auto-polish for you:
Install the "auto-polish" Claude Code mod from https://github.com/mako-code/gobworks/tree/main/mods/autopilot/auto-polish. Run claude plugin validate on it first and show me what it can access before you enable it.
More from mako-code/gobworks
This repository has at least 9 Claude Code mods on MCPMods.
- bench: Measures a command: warmup and timed runs, median/p95/stddev and outliers, two commands compared or a saved baseline per (Review before installing)
- best-of-n: Runs 2-4 attempts at a task in parallel git worktrees, each with a different approach; compare their diffs and adopt the (Review before installing)
- bisect: Finds the commit that broke something: git bisect with your test command in a temporary worktree (your working tree is n (High risk)
- canvas: Gives Claude a screen to draw on: SVG diagrams and Markdown reports in a Canvas pane with history. (Review before installing)
- council: More than one mind: ask several models at once and get a synthesis, critique the last answer, and let Claude consult ano (High risk)
- data-peek: Look into CSV, TSV, JSON and JSON Lines files without dumping them into context: schema, stats, rows, filters, group cou (Low risk)
- gh-inbox: GitHub issues and pull requests in a pane — one press to have Claude work on an issue or review a PR — plus the current (Review before installing)
- http-lab: An HTTP tool for API work: status, timing, trimmed headers and a body shaped to fit; localhost runs freely, other hosts (High risk)