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 skills add ejboy/agent-scripts --skill article-polishgit clone --depth 1 https://github.com/ejboy/agent-scriptsWrote 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/ejboy/agent-scripts/article-polish)<a href="https://agentmods.dev/skills/ejboy/agent-scripts/article-polish"><img src="https://agentmods.dev/badge/skills/ejboy/agent-scripts/article-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/ejboy/agent-scripts/article-polish"><img src="https://agentmods.dev/badge/skills/ejboy/agent-scripts/article-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 | $0.00078 | $0.00796 |
| Opus 5.5 | $0.00031 | $0.00318 |
| Sonnet 5.5 | $0.00016 | $0.00159 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
article-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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article polish
This is an experimental Agent Scripts skill.
Follow project instructions before this skill. Default to review only: do not modify files unless explicitly requested. Interpret requests as follows:
- "Review this article for readability" means report findings without editing.
- "Polish this article" or "Revise this article" explicitly requests targeted improvements; apply edits rather than automatically rewriting the whole article.
An explicit review-only or no-edit constraint takes precedence.
Read as the intended reader
Read the entire article before reporting findings. Establish its audience, genre, purpose, and tone from the request and draft; ask only when uncertainty materially affects the review. Adapt recommendations to that context, including what the audience already knows.
Look for meaningful reader friction:
- Repeated words, phrases, explanations, sections, or conclusions. Distinguish useful emphasis and reminders from repetition that adds nothing.
- Unnecessary hedging, verbose constructions, stiff or formulaic language, awkward transitions, and sentences whose complexity obscures the point.
- Overexplaining familiar concepts, paragraphs that interrupt the narrative, information introduced too early, missing context, and unclear connections.
- Claims whose wording leaves readers unsure whether they are facts, approximations, or illustrative examples.
Inspect visuals in context
Inspect actual screenshots, charts, and other visual assets when available, alongside their headings, captions, alt text, and surrounding prose. Use an available image viewer or rendered document; filenames and markup alone do not verify visual content. Identify inaccessible assets and their visual checks as unverified, while still reviewing the available text.
Check whether each visual teaches something useful and whether nearby text or other visuals repeat it unnecessarily. Captions should supply useful context rather than merely repeat a heading. Alt text should convey essential visual information; overlap with a caption can be necessary for accessibility, so do not remove it solely to avoid repetition.
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 First seen · 83 lines · 78 tokens per session scan A 56940dcaba81
article-polish is a skill published in the GitHub repository ejboy/agent-scripts (116 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 796 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
hyperframes
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation…
hatch-pet
Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to hatch a Codex pet, create a custom animated pet, or build a built-in pet asset with an 8x9 atlas, transparent unused cells…
od-contribute
One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship…
waitlist-page
Minimal pre-launch landing with email capture, brand logo, and optional decorative layer. Reads DESIGN.md for colors, typography, and layout rules. Best for: product launches, beta signups, early access programs, indie projects.
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…