Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/define-polish-standard.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/commands/bredmond1019/claude-sdk-rs/define-polish-standard)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/define-polish-standard"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/define-polish-standard/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/commands/bredmond1019/claude-sdk-rs/define-polish-standard"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/define-polish-standard.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 | $0.00000 | $0.02829 |
| Opus 5.5 | $0.00000 | $0.01132 |
| Sonnet 5.5 | $0.00000 | $0.00566 |
| Haiku 4.5 | $0.00000 | $0.00283 |
Grade A, and why
define-polish-standard 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 11d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Define Polish Standard — write the document a UI can actually be judged against.
Variables
$ARGUMENTS — what the standard covers, plus flags. Example: "the BastionUI operator app --surface mobile --slug surfaces-e2e"
| Flag | What it does |
|---|---|
--surface <web|mobile|tui|desktop> |
The surface kind. Repeatable — a product with a web app and a phone app gets one section per surface, because the rules differ |
--slug <name> |
Output goes to planning/<name>/polish-standard.md. Default: kebab-case of the description |
--from <path> |
An existing standard, style guide, or design doc to build on rather than replace |
--no-calibrate |
Skip the two-agent calibration. Only for a throwaway draft — never before an assessment reads it |
Purpose
"Clean and polished" cannot be assessed against nothing. Without a written standard you get opinions; opinions differ between reviewers; and opinions do not become blocks of work.
This command writes planning/<slug>/polish-standard.md: a falsifiable description of what
good looks like for this specific product, specific enough that two people shown the same
screenshot reach the same verdict.
It is the input a UI review reads — /assess's polish scout, a /ticket's acceptance criteria, a
reviewer's checklist. It is not a design system, a brand guide, or a redesign.
The test this document must pass: hand it plus one screenshot to two fresh agents and ask "does this pass?" If they disagree, the standard is not finished. That is step 6, and it is the point of the command.
Instructions
-
If
$ARGUMENTSis empty, stop and ask what surface to write a standard for. -
Resolve the surfaces. Take them from
--surface, or infer from the repo and confirm with the user before writing. Each named surface gets its own section — the rules genuinely differ, and a merged section produces items that are meaningless for one of them (touch targets on a TUI, hover states on a phone).
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.
- 11d ago First seen · 247 lines · 0 tokens per session scan A ca922632c424
define-polish-standard is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,829 tokens. 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 2026-10-26.
define-polish-standard compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| define-polish-standardbredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| pr-enhanceruvnet/ruflo | Command | 81k | today | MIT | A | 0 | Claude Code |
| test-featureLykhoyda/rn-dev-agent | Command | 20 | 12d ago | MIT | A | 30 | Claude Code |
| test-value-reviewoalders/kitchen-sink | Command | 5 | 3d ago | MIT | A | 58 | Claude Code |
| bug-checkyeaight7/agent-powerups | Command | 8 | 1mo ago | Apache-2.0 | A | 25 | Claude Code |
| claude-looprunnithan/claudex-setup | Command | 1 | 11d ago | MIT | B | 72 | Claude Code |
| security-sastzsutxz/ClaudeLearning | Command | 5 | 3mo ago | MIT | A | 17 | Claude Code |