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 blog-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/blog-writer)<a href="https://agentmods.dev/skills/travsteward/openwriter/blog-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/blog-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/blog-writer"><img src="https://agentmods.dev/badge/skills/travsteward/openwriter/blog-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 | $0.00240 | $0.03482 |
| Opus 5 | $0.00120 | $0.01741 |
| Sonnet 5 | $0.00048 | $0.00696 |
| Haiku 4.5 | $0.00024 | $0.00348 |
Grade A, and why
blog-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 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Writer
Channel-master skill for long-form blog content. Owns ideation → beats → draft → image → publish.
Architecture: beats-first (v0.5.0) + plugin-backed publish (v0.4.0). Each post lives in its own container with two sibling docs: a Beats doc (the structural commitments — beat list + title/preview/slug as B0) and a Draft doc (the voice-poured prose). Beats reshape regularly; draft re-pours via /authors-voice against a per-site anchor (voice/anchor-<site-slug>.md). Publish is a single post_to_blog MCP call against a site registered via add_blog_site — site-specific frontmatter (layout, author, prerender, date → publishedDate for Astro, etc.) lives on the github plugin's per-site config in ~/.openwriter/config.json, not in project config. Mirrors book-writer's discipline at post scale.
Convention
This skill obeys the shared writer contract at WRITER-CONVENTION.md. Brief shape and return shape match that doc. Sub-form values: long | short | tutorial | announcement.
OpenWriter pad mechanics are canonical in /openwriter — read it, don't re-derive from tool descriptions. The load-bearing rule: populate_document is create-only, used ONCE; it re-sends the whole body, so calling it again to "fix" a doc appends a duplicate. All edits (rewrite / insert / delete) go through write_to_pad on fresh node IDs. Plus the read ladder (outline_doc → search_docs → peek_doc → read_pad).
Blog posts ship SEO-complete in the FIRST pass. A blog post almost always carries SEO — internal/cluster links, meta + slug + tags, snippet-targeted headings, FAQ/schema-eligible content all go into the initial draft (the minion brief + first populate_document), never bolted on after. Bolting SEO on later forces an edit (→ write_to_pad, never a 2nd populate). SEO-strategy-led posts (pillar / landing / comparison) front-end through /seo-writer if you have it installed (not bundled with OpenWriter).
What ships with it
11 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.
- 10d ago First seen · 115 lines · 240 tokens per session scan A f2a53eca2c52
blog-writer is a skill published in the GitHub repository travsteward/openwriter (27 stars, last pushed 2d ago), licensed MIT. It adds 240 tokens to every session and 3,482 once invoked, about $0.0012 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
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…