scopewalker-mcp: Skill for Claude Code

.claude/skills/polish/SKILL.md

polish is a skill for Claude Code from timohaa/scopewalker-mcp. It costs 60 tokens per session (999 once invoked), scanned A, original, MIT.

A quality-check workflow that uses helper agents to fix lint, type, formatting, tests, coding standards, comments, documentation, and Markdown issues.

In plain words
What is it for?
Use it to check changed files or a whole codebase, run tests, enforce project rules, clean comments, and keep documentation in sync.
Why use it?
It collects several routine cleanup and verification tasks into one ordered process, reducing the chance that problems remain before code is delivered.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is timohaa/scopewalker-mcp's own configuration. It tells Claude Code how to work on scopewalker-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scopewalker-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to timohaa/scopewalker-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/timohaa/scopewalker-mcp/main/.claude/skills/polish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/timohaa/scopewalker-mcp

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/skills/timohaa/scopewalker-mcp/polish/github.svg)](https://agentmods.dev/skills/timohaa/scopewalker-mcp/polish)
Your own site
<a href="https://agentmods.dev/skills/timohaa/scopewalker-mcp/polish"><img src="https://agentmods.dev/badge/skills/timohaa/scopewalker-mcp/polish/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.

agentmods 80×15 button for polish

Your own site · 80×15
<a href="https://agentmods.dev/skills/timohaa/scopewalker-mcp/polish"><img src="https://agentmods.dev/badge/skills/timohaa/scopewalker-mcp/polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 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 $0.00060 $0.00999
Opus 5 $0.00030 $0.00500
Sonnet 5 $0.00012 $0.00200
Haiku 4.5 $0.00006 $0.00100

Measured 4d ago against content hash 1dc063b0f690, 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 4d 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/skills/polish/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Polish

Run the full quality pipeline as subagents launched via the Agent tool. Steps run sequentially except 4a/4b, which run in parallel (they edit disjoint file sets: src/**/*.ts vs *.md).

Scope

Default scope is changed files: comment-fixer processes recently changed .ts files only. /polish full passes full to comment-fixer for a whole-src/ comment sweep. Nothing else differs between the modes.

Pipeline

Run these subagents in this order using the Agent tool with the subagent_type shown below. Launch 4a and 4b as two Agent calls in a single message so they run concurrently; wait for both before step 5. Wait for every other step to complete before starting the next.

Step subagent_type Purpose
1 lint-type-format-fixer Fix all lint errors, type errors, and formatting issues so later agents work on clean code.
2 smart-test-fixer Run tests and fix any failures. Include in the prompt: "lint/typecheck was just verified green; start with npm run test only, and run npm run check only after you edit source files."
3 standards-enforcer Scan for coding standards violations (file length <300 lines, function length <100 lines, nesting depth, too many parameters) and fix them. Runs the full test suite only if it edited.
4a comment-fixer Clean up comments (remove redundant, fix misleading, ensure comments explain WHY not WHAT). Changed files by default; include full in the prompt only when polish was invoked with full. Runs npm run check only if it edited. Launch together with 4b.
4b docs-reality-sync Audit and sync documentation (README.md, TOOLS.md, docs/, AGENTS.md, .claude/) with the final codebase state. Launch together with 4a.
5 agents-md-enforcer Audit AGENTS.md (and its @path imports) against Anthropic's Claude Code best practices: prune derivable, redundant, or platitudinous content; tighten vague rules; verify references. Runs after 4b so pruning sees the fact-checked content.
6 markdown-quality-fixer Lint and format all modified markdown files. Runs last to catch .md changes from earlier steps (especially docs-reality-sync and agents-md-enforcer).

Read the full file on GitHub · 68 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. 4d ago Changed · -1 lines 1dc063b0f690
  2. 8d ago First seen · 69 lines · 60 tokens per session scan A 1883b5de4c45

Subscribe to this mod's changes

polish is a skill published in the GitHub repository timohaa/scopewalker-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 999 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.