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.
curl -O https://raw.githubusercontent.com/timohaa/scopewalker-mcp/main/.claude/skills/polish/SKILL.mdgit clone --depth 1 https://github.com/timohaa/scopewalker-mcpWrote 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/skills/timohaa/scopewalker-mcp/polish)<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.
<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>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 | $0.00060 | $0.00999 |
| Opus 5 | $0.00030 | $0.00500 |
| Sonnet 5 | $0.00012 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
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.
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). |
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.
- 4d ago Changed · -1 lines 1dc063b0f690
- 8d ago First seen · 69 lines · 60 tokens per session scan A 1883b5de4c45
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.
Other skills, from other repositories
setup-config
Analyze a repository and generate an intelligent omen.toml with project-specific defaults. Use when starting Omen in a new project.
track-trends
Analyze repository health trends over time using historical git commits. Use for quarterly reports, release retrospectives, or tracking technical debt paydown progress.
assess-impact
Analyze blast radius before changing specific files. Use before refactoring core components, making breaking API changes, or modifying shared code to identify affected files and stakeholders.
audit-architecture
Audit module coupling, cohesion, hidden dependencies, and design smells. Use when conducting architecture reviews, evaluating design decisions, or identifying structural tech debt.
onboard-codebase
Generate onboarding guide with key symbols, architecture overview, and subject matter experts. Use when joining a new project, onboarding teammates, or creating project documentation.
report-debt
Generate comprehensive tech debt assessment with quantified metrics and prioritized issues. Use for sprint planning, stakeholder reports, or justifying refactoring time allocation.