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 editor-note-writergit 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/editor-note-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/editor-note-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/editor-note-writer/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/editor-note-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/editor-note-writer.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 | $0.00035 | $0.01242 |
| Opus 5 | $0.00017 | $0.00621 |
| Sonnet 5 | $0.00007 | $0.00248 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
editor-note-writer 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editor Note Writer
What This Skill Does
Drafts a publication-ready editor's note — correction, clarification, update, or disclosure — from the facts you provide, following standard editorial transparency conventions.
When To Use This Skill
- A published article contains a factual error and you need a correction note appended or prepended to the piece
- New information has emerged since publication and readers need an update notice
- An editorial decision requires disclosure — a conflict of interest, a source who has since recanted, or a legal outcome that changes the story
- You need to clarify ambiguous wording that generated reader complaints without issuing a formal correction
What You Need To Provide
Required: The type of note (correction, clarification, update, or disclosure); a plain-language description of what happened — what was wrong or what changed; the article title or identifier so the note can reference it.
Optional: The publication date of the original article; the specific sentence or passage that is affected; any house style rules for how your publication formats editor's notes (e.g., "We use 'Correction:' in bold at the top of the article"); whether the note should be appended, prepended, or standalone.
How the Assistant Approaches This
-
Classifies the note type. Determines whether this is a correction (something was factually wrong), a clarification (something was technically accurate but misleading), an update (new information has emerged), or a disclosure (editorial transparency about process or conflicts). Each type has a different conventional tone and structure.
-
States the error or change plainly. Writes what was originally published, what was incorrect or incomplete, and what the accurate version is — in that order. Uses neutral, non-defensive language. Never blames sources, readers, or circumstances. Never minimises the error.
-
Calibrates length and tone to severity. A minor factual correction (wrong date, misspelled name) gets two sentences. A substantive correction that changes the meaning of a key claim gets a full paragraph with context. A disclosure or update that affects editorial credibility gets careful, measured language that acknowledges the significance without being melodramatic.
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 · 74 lines · 35 tokens per session scan A 31886e06ac97
editor-note-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 1,242 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
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…
voice-update
Update context/voice-and-style.md or context/about-me.md from one of three sources. Manual (user dictates a single new rule, sample, or career fact). Memory (batch pull from Claude Code's auto-memory in /.claude/projects/ /memory/). Sent-mail (analyze the last 20-50 sent Gmail messages and propose updates from…
warmth-and-competence
Audits a draft on Susan Fiske's two-axis model of social judgment — warmth (do I like and trust this person?) and competence (do I respect this person?) — and rewrites the lines that signal the wrong thing on either axis. Implements Kramon's hardest rule: "show competence AND warmth in a single sentence." Use when a…