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.
npx agentmods add skills/an2n/ghostwriter/polishnpx skills add an2n/ghostwriter --skill polishgit clone --depth 1 https://github.com/an2n/ghostwriterWrote 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/an2n/ghostwriter/polish)<a href="https://agentmods.dev/skills/an2n/ghostwriter/polish"><img src="https://agentmods.dev/badge/skills/an2n/ghostwriter/polish.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.04830 |
| Opus 5 | $0.00057 | $0.02415 |
| Sonnet 5 | $0.00023 | $0.00966 |
| Haiku 4.5 | $0.00011 | $0.00483 |
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 3d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish
Rewrites text to move it toward the statistical and stylistic shape of human writing.
This is a rewrite-only skill - it never scores anything. See check for the audit
side; the two are companions but operate independently.
Six moves, apply all of them
Not a checklist to pick from - every move gets applied on every rewrite. Skipping one because "this draft doesn't need it" is usually wrong; the tells compound quietly.
Move 1: Word choice
Swap predictable vocabulary for what a person would actually reach for in context:
- Generic verb → specific one: "address" → "untangle", "utilize" → "lean on", "implement" → "wire up"
- Let the subject matter pick the words: a backend engineer says "flush the buffer," not "clear the temporary data storage"
- One or two genuinely surprising but accurate word choices per paragraph
- Cut on sight: delve, leverage (verb), robust, streamline, significant, comprehensive, notably, it is worth noting, in today's fast-paced world
Elegant variation. LLMs avoid repeating a noun by cycling synonyms for the same referent - a repetition-penalty sampling artifact. "The founder built the company. The entrepreneur later sold it. The visionary now advises startups." Same person, three labels. Fix: pick the canonical noun and reuse it, or use a pronoun for variation. Synonym-cycling is detectable; pronoun reference reads human.
Copula avoidance. "Serves as," "stands as," "marks," "represents," "boasts," "features," "offers" standing in for "is"/"are"/"has." "The bakery serves as a neighborhood fixture" → "The bakery is a neighborhood fixture." Use the plain verb.
Inflated significance. "Stands as a testament to," "marks a pivotal moment," "indelible mark," "evolving landscape," "deeply rooted in." Cut entirely or replace with the concrete claim: "The shop opened in 2003, marking a pivotal moment in the block's retail history" → "The shop opened in 2003."
Brochure language. "Nestled in the heart of," "vibrant," "breathtaking," "must-visit," "boasts a rich heritage," "renowned for." Cut it. "Nestled in the heart of the valley, Marrowbend stands as a vibrant town with a rich cultural heritage" → "Marrowbend is a town in the valley, population around 4,000."
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.
- 3d ago First seen · 389 lines · 114 tokens per session scan A cb6e398186c2
polish is a skill published in the GitHub repository an2n/ghostwriter (1 stars, last pushed 7d ago), licensed MIT. It adds 114 tokens to every session and 4,830 once invoked, about $0.0006 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
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
clean-user-facing-text
Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".