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 travsteward/openwriter --skill newsletter-writergit clone --depth 1 https://github.com/travsteward/openwriterWrote 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/travsteward/openwriter/newsletter-writer)<a href="https://agentmods.dev/skills/travsteward/openwriter/newsletter-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/newsletter-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/travsteward/openwriter/newsletter-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/newsletter-writer.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 | $0.00118 | $0.08078 |
| Opus 5 | $0.00059 | $0.04039 |
| Sonnet 5 | $0.00024 | $0.01616 |
| Haiku 4.5 | $0.00012 | $0.00808 |
Grade A, and why
newsletter-writer scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL "{image_url}" -o ~/.openwriter/profiles/Default/_images/{descriptive-name}.jpg How it starts
The opening of the file, as written. The whole thing — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Newsletter Writer Skill — /newsletter-writer
Weekly newsletter pipeline: scaffold structure, gather data, query the author, synthesize in their voice, review, send.
Worked example throughout: a fictional newsletter, The Sleep Brief, written by a popular-science sleep author whose community site is deeprest.example.com and whose X handle is @sleepauthor. Substitute your own newsletter name, brand, domain, and handle — they live in your project's config.md (see Configuration).
Philosophy
This newsletter is behind the scenes, not a content recap. Readers can go read the tweets and articles themselves. The newsletter gives them what they can't get anywhere else: WHY the author wrote it, what they were trying to achieve, the deeper reasoning that didn't fit in 280 characters, and how the author's project interacted with the world that week. Every section answers "what was I thinking?" not "what did I post."
Commands
/newsletteror/newsletter draft— Full pipeline: scaffold → gather → query → enhanced scaffold → draft → review/newsletter scaffold— Create doc with empty skeleton structure (header, HRs, placeholder sections, footer)/newsletter gather— Data collection only (metrics, top tweets, article)/newsletter review— Pre-send checklist + /polish 90/100 scoring on every section/newsletter send— Send via OpenWriter newsletter system/newsletter status— Subscriber count, last sent, domain status
Critical Rules
- ALWAYS use the authors-voice protocol. Load the voice profile/anchor, pull writing samples from the corpus, write with the profile as behavioral constraints, run anti-AI detection. Never skip this. The authors-voice skill ships with the OpenWriter authors-voice plugin.
- NEVER write the author's position for them. You gather data and present structure. You ASK the author what they think. They tell you. You synthesize their input in their voice. The author's original thinking is the product — you are the editor, not the writer.
- Source article content from OpenWriter docs FIRST. X Articles may not be readable via fxtwitter. The drafts live in OpenWriter. Search
list_documentsbefore trying external APIs. - Every section headline is specific to that week's content. No generic recurring labels like "This Week on X" or "The Author's Position." Each section gets a unique, attention-grabbing headline based on the actual topic. Example: "Why the 8-Hour Rule Is Wrong for Shift Workers" not "The Author's Position." "The Tweet That Got 1.75M Views About Sleep Debt" not "This Week on X." Specificity is what grabs attention.
- No outbound links except the footer CTA. The newsletter summarizes and screenshots everything — readers don't need to leave. No "View the post →" or "Read the full article →" links to X or anywhere else. The only link in the entire newsletter is the footer CTA to your brand site. Every other link is a leak.
What ships with it
2 files 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.
- 12d ago First seen · 618 lines · 118 tokens per session scan A 03b6141e549d
newsletter-writer is a skill published in the GitHub repository travsteward/openwriter (27 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 8,078 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
humanize-pro
Use when the user asks to humanize, unslop, de-slop, de-AI, clean up, tighten, or make text sound human or natural; when they say something reads like AI or like ChatGPT; when they ask whether something matches their voice or style guide; or when drafting or rewriting outbound human communication: LinkedIn posts and…
anti-ai-writing
Use when writing or editing any prose for a human reader - documentation, READMEs, emails, reports, captions, scripts, blog posts, UI copy, commit messages, PR descriptions - or when asked to remove AI tells, de-slop text, make writing sound human, or check writing style. Applies 29 researched patterns that make text…
anti-slop
Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize…
humanizer-workbench
Rewrites AI-generated text into natural, human-quality writing using a multi-stage detection and transformation pipeline.
writing-humanizer
A text-editing skill that removes patterns often associated with AI-written prose and makes writing sound more natural. Its instructions are aimed mainly at Traditional Chinese text used in Taiwan.
kill-slop
Audit a file or draft for AI slop and off-voice lines against the author's bound voice, report findings with in-voice swaps, then apply approved fixes. Use when the user says "kill slop", "/kill-slop [file]", "find the slop in this", "audit this for slop", or wants a deck, article, page, or draft cleaned to sound like…