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 ur-grue/autopunk-media-skills --skill proofreadergit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/proofreader)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/proofreader"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/proofreader/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/ur-grue/autopunk-media-skills/proofreader"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/proofreader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01294 |
| Opus 5 | $0.00018 | $0.00647 |
| Sonnet 5 | $0.00007 | $0.00259 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
proofreader 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 10d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proofreader
What This Skill Does
Proofread a piece of text and return it with all spelling, grammar, punctuation, and typographical errors corrected — preserving the author's voice and intentional style choices throughout.
When To Use This Skill
- You are doing a final check before publishing an article, caption, press release, or broadcast script
- You need to verify that translated or adapted copy has not introduced language errors during revision
- You are reviewing user-generated or community-submitted content before it goes live
- You have written a draft quickly under deadline and want a clean error pass before sending to an editor
- You need to check headlines, subheadings, pull quotes, or captions that are often missed in a full-document proofread
What You Need To Provide
Required: The text to proofread.
Optional: Language variant (British English, American English, Australian English — defaults to British English if not specified); house style notes (e.g. "Oxford comma: yes", "spell out numbers under ten", "capitalise 'Government' when referring to the UK Government"); whether to flag style choices for review rather than correcting them silently.
How the Assistant Approaches This
- Reads the full text for meaning before making any corrections — understanding the author's intent, register, and deliberate style choices (sentence fragments for effect, informal voice, rule-breaking for emphasis)
- Makes a correction pass for spelling errors, grammatical mistakes, punctuation errors, and typographical issues (doubled words, missing words, transposed letters), distinguishing between genuine errors and intentional stylistic decisions
- Returns the corrected text in full, followed by a numbered change log listing every correction made — the original, the corrected version, and the reason — so the author can review and accept or reject each change individually
Output Format
Two sections:
Corrected text — the full text with all errors fixed. No annotations or markup in the text itself unless track-changes format was requested.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 89 lines · 36 tokens per session scan A bd4bf34c5169
proofreader is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 1,294 once invoked, about $0.0002 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.
Other skills, from other repositories
grammar-and-mechanics
Provides a structured reference for the grammar and punctuation rules that most frequently undermine credibility in business writing. Covers subject-verb agreement, pronoun case, dangling modifiers, parallel construction, comma splices, and the most common usage confusions (affect/effect, that/which, who/whom). Use…
revising-and-editing
Teaches the distinct disciplines of revising (rethinking content and structure) and editing (refining sentences and word choices), with a concrete three-draft evolution showing how a mediocre memo transforms into an excellent one. Covers revision checklists, editing checklists, and the peer feedback process. Use when…
compression
Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific number (200 for a cold email, 500 for an op-ed, 6 for a product summary). redundancy catches the specific failure where a phrase says what the verb or context already implied — "going forward" after a…
vividness
Pushes a draft from abstract toward concrete at two scales. Noun-level (replaces "dog" with "German shepherd," "customer" with "Sarah at JPMorgan's options-trading desk," "many" with "47 of 100") and scene-level (turns "I was angry" into the body signal, room, and dialogue). Implements Kramon's "specific over…
dealing-with-reporters
Drafts and reviews answers to reporter questions, on-the-record statements, crisis-comms responses, and press-inquiry replies. Implements Andrew Ross Sorkin's 11 rules (taught with Kramon at Stanford GSB) plus AP attribution definitions for off-the-record / background / deep background conversations. Use when a…
sent-mail-outcome-tracker
Read the user's recent cold-outreach sent mail, look up which messages got replies, classify reply sentiment, and produce an outcome report that surfaces what the responders had in common. Use when the user says "did my cold emails get replies," "what's my reply rate," "sent-mail outcomes," "track outcomes," or…