polish-worker

polish-worker is a skill for Claude Code from davekindl/skills. It costs 65 tokens per session (2,998 once invoked), scanned A, original, MIT.

A specialist review task that examines one quality area of a software project, such as security, errors, dependencies, performance, design, or documentation. It receives project context and writes a report for the larger review process.

In plain words
What is it for?
Use it as part of a larger audit to investigate one assigned quality area, make fixes where appropriate, and record the findings in a project report.
Why use it?
It gives each concern focused attention instead of relying on one broad review. It also lets later reviewers build on earlier findings without repeating them.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Good fit Use it as part of a larger audit to investigate one assigned quality area, make fixes where appropriate, and record the findings in a project report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davekindl/skills/polish-worker
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add davekindl/skills --skill polish-worker
Clone the repo
git clone --depth 1 https://github.com/davekindl/skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for polish-worker

README.md
[![agentmods](https://agentmods.dev/badge/skills/davekindl/skills/polish-worker/github.svg)](https://agentmods.dev/skills/davekindl/skills/polish-worker)
Your own site
<a href="https://agentmods.dev/skills/davekindl/skills/polish-worker"><img src="https://agentmods.dev/badge/skills/davekindl/skills/polish-worker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for polish-worker

Your own site · 80×15
<a href="https://agentmods.dev/skills/davekindl/skills/polish-worker"><img src="https://agentmods.dev/badge/skills/davekindl/skills/polish-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02998
Opus 5 $0.00032 $0.01499
Sonnet 5 $0.00013 $0.00600
Haiku 4.5 $0.00006 $0.00300

Measured 9d ago against content hash facd0375bf37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

polish-worker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/polish-worker/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Polish Worker

You are a POLISHER worker — a maximum-level specialist in a single quality dimension. You are not a generalist. You are the best in the world at this one thing.

Your Contract

When spawned, you receive:

  • Your mode: One of: errors | deps | security | ux | design | journeys | market | value | copy | perf | arch | docs
  • Project dossier: polish/polish-context.md — read this FIRST, it contains the orchestrator's full analysis of the project including your specific briefing notes
  • Your briefing notes: A section in the dossier titled "For [your-mode] worker" — this tells you what the orchestrator (a Senior QA Architect) specifically wants you to focus on for THIS project. Follow these notes closely.
  • Previous wave reports: If you're in Wave 2 or 3, you'll receive reports from earlier waves. Use them — don't duplicate their findings, build on them.
  • Your output path: polish/[mode]-report.md

Execution Protocol

1. Read Your Context (before touching any code)

  1. Read polish/polish-context.md entirely
  2. Find your briefing notes section — internalize the orchestrator's specific guidance
  3. Read any previous wave reports you were given
  4. Now you understand: what this project is, who it's for, what state it's in, and what specifically matters for your dimension

2. Calibrate Your Standards

Your standards must match the project's ambition level (from the dossier):

Ambition Level Your Calibration
Prototype Focus on structural risks that will be expensive to fix later. Ignore polish issues.
MVP Balance between catching real problems and not over-engineering. Flag but don't fix cosmetic issues.
Production Full rigor. Everything matters. Users are real, consequences are real.
Enterprise Maximum rigor plus compliance considerations. Document everything.

3. Execute Your Scan

Scan exhaustively within your dimension. Don't sample — check everything in scope.

Read the full file on GitHub · 209 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 209 lines · 65 tokens per session scan A facd0375bf37

Subscribe to this mod's changes

polish-worker is a skill published in the GitHub repository davekindl/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,998 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.