polish

A command that reviews existing code and addresses the problems it finds. Each finding is either fixed or left with an explanation of why it can be deferred.

In plain words
What is it for?
Polishing uncommitted changes, changes since a branch, or work associated with a pull request by fixing or documenting review findings.
Why use it?
It turns a code review into a follow-up pass that can resolve issues instead of only listing them.

Command for Claude Code

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.

agentmods
npx agentmods add commands/wbern/agent-instructions/polish
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.01414
Opus 5 $0.00006 $0.00707
Sonnet 5 $0.00003 $0.00283
Haiku 4.5 $0.00001 $0.00141

Measured 2d ago against content hash 9843797952e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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/commands/polish.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

Polish

Take another pass at existing work to address issues. Unlike /code-review which only identifies problems, /polish resolves each finding by either:

  1. Fixing - Implement the improvement
  2. Skipping with justification - Document why the issue can be deferred or ignored

Phase 0: Determine Scope

Parse the argument to determine what to polish:

Input Action
No argument Detect divergence point, review uncommitted + committed changes
Branch name Changes from that branch to HEAD
PR number (e.g., 123) Fetch PR diff from GitHub
PR URL (e.g., github.com/.../pull/123) Extract PR number and fetch diff
File/path Focus on specific file(s)

For GitHub PRs:

  1. Try GitHub MCP first: mcp__github__pull_request_read with method: "get_diff"
  2. Fall back to gh CLI: gh pr diff <number>
  3. If neither works, report error and stop

For local branches:

  1. Get current branch: git rev-parse --abbrev-ref HEAD
  2. Detect divergence point (same logic as /code-review)
  3. Collect changed files from diff and uncommitted changes

Phase 1: Identify Issues

Categorize files based on these patterns:

Category File Patterns
Frontend/UI *.tsx, *.jsx, components/, pages/, views/, *.vue
Frontend/Styling *.css, *.scss, *.less, styles/, *.tailwind*, *.styled.*
Backend/API routes/, api/, controllers/, services/, *.controller.*, *.service.*, *.resolver.*
Backend/Data migrations/, models/, prisma/, schema.*, *.model.*, *.entity.*
Tooling/Config scripts/, *.config.*, package.json, tsconfig.*, vite.*, webpack.*, eslint.*
CI/CD .github/, .gitlab-ci.*, Dockerfile, docker-compose.*, *.yml in CI paths
Tests *.test.*, *.spec.*, __tests__/, __mocks__/, *.stories.*
Docs *.md, docs/, README*, CHANGELOG*

Read the full file on GitHub · 189 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. 2d ago First seen · 189 lines · 13 tokens per session scan A 9843797952e6

Subscribe to this mod's changes

polish is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,414 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 2026-08-30.