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.
npx skills add davekindl/skills --skill polish-workergit clone --depth 1 https://github.com/davekindl/skillsWrote 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.
[](https://agentmods.dev/skills/davekindl/skills/polish-worker)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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)
- Read
polish/polish-context.mdentirely - Find your briefing notes section — internalize the orchestrator's specific guidance
- Read any previous wave reports you were given
- 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.
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.
- 9d ago First seen · 209 lines · 65 tokens per session scan A facd0375bf37
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…