polish

polish is a skill for Claude Code from takubii/smithy. It costs 48 tokens per session (484 once invoked), scanned A, original, MIT.

A review procedure for checking a completed code change before approval or a pull request. It compares the change with its intended result, acceptance criteria, non-goals, relevant files, and verification.

In plain words
What is it for?
Use it to review non-trivial changes before final approval or opening a pull request; trivial documentation edits and obvious one-file fixes may be skipped.
Why use it?
It adds an independent check for missed edge cases, missing tests, behavior that does not meet the request, or unrelated changes. It is normally used after implementation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the smithy plugin — 4 skills shipped together

Good fit Use it to review non-trivial changes before final approval or opening a pull request; trivial documentation edits and obvious one-file fixes may be skipped.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/takubii/smithy/polish
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 takubii/smithy --skill polish
Clone the repo
git clone --depth 1 https://github.com/takubii/smithy

Made for: Claude Code.

Or install smithy, the plugin that ships this one along with the rest of its 4 skills.

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/skills/takubii/smithy/polish.svg)](https://agentmods.dev/skills/takubii/smithy/polish)
Your own site
<a href="https://agentmods.dev/skills/takubii/smithy/polish"><img src="https://agentmods.dev/badge/skills/takubii/smithy/polish.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 484 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 $0.00048 $0.00484
Opus 5 $0.00024 $0.00242
Sonnet 5 $0.00010 $0.00097
Haiku 4.5 $0.00005 $0.00048

Measured 7d ago against content hash 2cdf2c358080, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

claude-code/plugins/smithy/skills/polish/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

polish

Run an independent review protocol after implementation.

Run condition

Run after implementation and before final approval or PR unless the change is trivial, such as docs-only edits, renames, or an obvious one-file fix.

Review delegation

For non-trivial changes, use Task to run an independent reviewer. The reviewer should inspect the change against the intent and return findings only. Do not ask the reviewer to apply fixes or make adoption decisions.

Reviewer input

Give the reviewer:

  • User intent.
  • Acceptance criteria.
  • Non-goals.
  • Current diff.
  • Relevant files or tests.
  • Verification already run.
  • Previously rejected findings and reasons, if any.

Do not give:

  • The implementer's detailed rationale.
  • A defense of the chosen design.
  • The expected answer.
  • Unnecessary conversation history.

Reviewer prompt shape

Ask for material findings only:

Review this change against the stated intent.

Intent:
...

Acceptance criteria:
...

Non-goals:
...

Verification already run:
...

Review target:
<diff and relevant files>

Focus on:
1. Behavior that does not satisfy the intent.
2. Missing edge cases or tests.
3. Unnecessary or unrelated changes.
4. Inconsistency with nearby code or existing conventions.

Do not suggest broad refactors outside the intent.
Do not re-litigate non-goals or previously rejected findings unless new evidence changes the premise.

Return findings only. If there are no material findings, say so.
For each finding include severity, evidence, why it matters, and suggested fix.

Output format

Return:

## Findings

- Severity:
  Evidence:
  Why it matters:
  Suggested fix:

## Review recommendation

- Adopt / reject / defer suggestions are advisory only.
- Recommend another round only if material changes are made.

## Convergence

- No material findings / needs adjudication / review cap reached.

Boundaries

Do not apply fixes. Do not make final adoption decisions. Verify every finding against primary sources before acting.

Read the full file on GitHub · 98 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. 7d ago First seen · 98 lines · 48 tokens per session scan A 2cdf2c358080

Subscribe to this mod's changes

polish is a skill published in the GitHub repository takubii/smithy (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 484 once invoked, about $0.0002 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.