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 copy-editor-assistantgit 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/copy-editor-assistant)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/copy-editor-assistant"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/copy-editor-assistant/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/copy-editor-assistant"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/copy-editor-assistant.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 | $0.00038 | $0.02091 |
| Opus 5 | $0.00019 | $0.01045 |
| Sonnet 5 | $0.00008 | $0.00418 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
copy-editor-assistant 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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Editor Assistant
What This Skill Does
Reviews a draft article and returns a structured list of grammatical errors, style inconsistencies, and clarity issues — each flagged with a specific suggested correction and a brief rationale.
When To Use This Skill
- You need a copy edit pass and don't have an editor available
- You want a systematic pre-submission check before sending a draft to an editor
- You're copy editing a piece written by someone else and want to work from a flagged list rather than reading through cold
- You're working on a tight deadline and need to prioritize the most significant issues in a long draft
What You Need To Provide
Required: The draft text (or the section you want reviewed); the style standard you're writing to (AP, Chicago, Guardian, house style, or "general professional journalism"). Optional: Specific areas of concern (e.g., "I'm not confident about the punctuation in complex sentences," "check all hyphenation," "flag any passive voice that weakens a sentence"); word count of the piece (helps calibrate the depth of the review); whether this is a first draft (light touch) or a final draft (thorough line edit).
How the Assistant Approaches This
- Reads the full draft and categorizes issues into three tiers: Tier 1 (errors — things that are wrong by the stated style standard and must be changed), Tier 2 (inconsistencies — things that are used two different ways in the same piece and need to be made consistent), and Tier 3 (suggestions — things that are not wrong but would benefit from rewording for clarity or flow).
- For each flagged item: quotes the original text, provides the correction, and gives a one-line rationale citing the rule or reason (not just "fix this").
- Returns items in document order so the writer can work through them linearly. Ends with a brief summary: how many Tier 1, 2, and 3 items, and an overall verdict on the draft's readiness (ready to submit, needs one more pass, requires significant line editing).
- After the summary, provides a "Next Step" note: work through Tier 1 items first (in document order), run fact-check-prompt separately for any statistical or attributed claims, and confirm with the specific publication's house style guide if using general AP/Chicago standards
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.
- 8d ago First seen · 109 lines · 38 tokens per session scan A 142598d2b77e
copy-editor-assistant is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 11d ago), licensed MIT. It adds 38 tokens to every session and 2,091 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 2026-09-04.
Other skills, from other repositories
design-dna
Use when a design has won and its look must survive: codify it into a permanent style skill with measured ratios, bans and tests that can fail, then build new pieces in that exact look. Fires on 'turn this into a skill', 'keep the same style', 'my output drifted'. NOT finding the winner (that is design-loop), NOT the…
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…
style-tells
Scrubs the three surface tells that make prose feel AI-generated, padded, or jargon-heavy. Three targets behind one skill, picked via the --target arg. em-dashes (default off in cold email / memo / Slack, max one per page in op-eds), adverbs (the -ly and intensifier pile), jargon (the Silicon Valley / consultant…
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…