agentmods.dev

polish

polish is a command for Claude Code from obiwancenobi/klamben. It costs 28 tokens per session (325 once invoked), scanned A, original, Apache-2.0.

A command for final, low-risk cleanup of Flutter code before it is shipped. Flutter is a toolkit for building app screens from reusable code components.

In plain words
What is it for?
Use it to add constant constructors and list keys, remove unused imports and commented-out code, improve labels and error messages, and format multi-line arguments.
Why use it?
It removes small quality problems without changing the program's logic or structure. This makes the code and user-facing text more consistent before a merge or release.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

not rated 2repo 5mo ago A scan 28 tokens original Apache-2.0

Good fit Use it to add constant constructors and list keys, remove unused imports and commented-out code, improve labels and error messages, and format multi-line arguments.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/obiwancenobi/klamben/polish
View source ↗ obiwancenobi/klamben beetlix.com
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.

Clone the repo
git clone --depth 1 https://github.com/obiwancenobi/klamben

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/obiwancenobi/klamben/polish.svg)](https://agentmods.dev/commands/obiwancenobi/klamben/polish)
Your own site
<a href="https://agentmods.dev/commands/obiwancenobi/klamben/polish"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/polish.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 325 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 $0.00028 $0.00325
Opus 5 $0.00014 $0.00162
Sonnet 5 $0.00006 $0.00065
Haiku 4.5 $0.00003 $0.00032

Measured 8d ago against content hash 6a9e89cba076, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

polish 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 8d 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.

src/commands/polish.md · 53 lines

What it actually says

/polish

Last-mile cleanup before shipping. Only safe, mechanical changes.

When to use

  • Before creating a PR
  • Before merging to main
  • After /audit shows only info-level issues

Actions

  1. Check design context: If .klamben.md exists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below.
  2. Add const to every eligible constructor (respects prefer_const_constructors lint)
  3. Add key: ValueKey(...) to list children that lack keys
  4. Remove unused imports
  5. Remove commented-out code blocks
  6. Tighten button labels and error messages (generic → specific)
  7. Add trailing commas to multi-line arg lists (for consistent formatting)

Do NOT

  • Refactor logic
  • Restructure widgets
  • Rename variables
  • Touch tests unless they break from the edits above

Output

polish lib/screens/home.dart

+ const Text('Welcome')
+ const SizedBox(height: 16)
- // TODO: remove this old code
- Container(child: ... // unused)
- 'Submit' → 'Save changes'

8 edits in 1 file.
Run tests before committing.
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. 8d ago First seen · 53 lines · 28 tokens per session scan A 6a9e89cba076

Subscribe to this mod's changes

polish is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 325 once invoked, about $0.0001 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.

Code reviewagent-skillsaiai-harnessdesign-skillsflutterslash-command
Related

Other commands, from other repositories

review-ticket

Review a ticket or PR through focused specialist lenses: scope, architecture, security, tests, AC coverage, and PR metadata.

HoangNguyen0403/agent-skills-standard · 0 tokens

code-review

Run an AI-assisted PR code review using multi-layer lenses with confidence scoring.

HoangNguyen0403/agent-skills-standard · 0 tokens

codebase-review

Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.

HoangNguyen0403/agent-skills-standard · 0 tokens

is-not-duplicated

please investigate the codebase based on your changes - do we have code duplication? After analysis, write updates to DUPLICATIONREPORT.md with the results. Keep in mind that other agents could keep their records, so you need to check the document first, decided to update or add new information.

Arenukvern/mcp_flutter · 0 tokens

explain

Drive a diff/PR/branch → self-contained interactive HTML explainer via the oma-explanation skill. Resolves the target ref, runs secret gates and the validation checklist, saves under .agents/results/explain/, and reports TL;DR plus path.

first-fluke/fullstack-starter · 51 tokens

review

Full QA review pipeline covering security audit (OWASP Top 10), performance analysis, accessibility check (WCAG 2.2 AA), and code quality review.

first-fluke/fullstack-starter · 32 tokens