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 x-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/x-writer)<a href="https://agentmods.dev/skills/travsteward/openwriter/x-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/x-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/x-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/x-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 | $0.00163 | $0.02153 |
| Opus 5 | $0.00081 | $0.01077 |
| Sonnet 5 | $0.00033 | $0.00431 |
| Haiku 4.5 | $0.00016 | $0.00215 |
Grade A, and why
x-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 9d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Writer
The writing format for X content. This skill defines HOW to write — not WHAT to write about. Apply these patterns to all tweets, threads, quote tweets, and replies.
Core Philosophy
The line-by-line style is dead. Broken up, one-sentence-per-line writing signals EFFORT. It says "I am trying to get your attention." People see through it. They turn off. The pithy fragment style is the format of engagement farmers, not thinkers.
We write in paragraphs. Clean, flowing, natural paragraphs. Like a smart person talking to you, not a copywriter performing for you. The authority comes from the IDEAS, not the formatting tricks.
The Fischerian Hook
Named after Fischer King (@FischerKing64), who demonstrates the pattern naturally.
The first sentence of every paragraph is the hook. It's a strong, declarative statement that pulls the reader in. Not a question. Not a teaser. A position.
Examples from Fischer King:
"The worst part about people in white collar professions claiming they work '80-100 hours a week' is that they are all liars."
"Every living President is watching Trump and realizing he lost the opportunity to shape the future of the country."
"The most disturbing aspect of Gordon Ramsay's 'Kitchen Nightmares' is the revelation that so many restaurants are just microwaving your meal."
The hook is a complete thought that makes you want the next sentence. The paragraph then builds, explains, or lands the point. The hook isn't bait — it's the thesis.
What a Fischerian Hook is NOT:
- "Here's what nobody tells you about X..." (teaser bait)
- "I need to talk about something." (vague attention grab)
- "This." followed by a screenshot (lazy engagement)
- One-word sentences for "impact" (performance writing)
Format: Medium Form
Optimal length: 4-5 paragraphs. Range: 3-6. This is the sweet spot for extended thought without losing attention.
- 3 paragraphs — minimum for a real argument. Setup, development, landing.
- 4-5 paragraphs — optimal. Enough room to build a framework, give evidence, and close with impact.
- 6 paragraphs — maximum before you're writing an article. If you need more, make it a thread or an X Article.
What ships with it
15 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.
- docs/article-format.md 7.8 KB
- docs/comics.md 3.5 KB
- docs/comics/characters.md 2.8 KB
- docs/comics/styles.md 3.7 KB
- docs/comics/workflow.md 6.2 KB
- docs/images.md 5.3 KB
- docs/images/characters.md 2.8 KB
- docs/images/styles.md 3.7 KB
- docs/images/workflow.md 5.3 KB
- docs/openwriter-mechanics.md 8.6 KB
- docs/pipeline.md 5.3 KB
- scripts/.gitignore 44 B
- scripts/generate-image.js 5.4 KB runs code
- scripts/package.json 343 B
- scripts/polish.js 5.9 KB runs code
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.
- 9d ago First seen · 147 lines · 163 tokens per session scan A 6c841f57ff40
x-writer is a skill published in the GitHub repository travsteward/openwriter (27 stars, last pushed today), licensed MIT. It adds 163 tokens to every session and 2,153 once invoked, about $0.0008 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
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…
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, X, cold or…
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…