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 lumizone/blog-writer-claude-skill --skill blog-writergit clone --depth 1 https://github.com/lumizone/blog-writer-claude-skillWrote 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/lumizone/blog-writer-claude-skill/blog-writer)<a href="https://agentmods.dev/skills/lumizone/blog-writer-claude-skill/blog-writer"><img src="https://agentmods.dev/badge/skills/lumizone/blog-writer-claude-skill/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/lumizone/blog-writer-claude-skill/blog-writer"><img src="https://agentmods.dev/badge/skills/lumizone/blog-writer-claude-skill/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 | $0.00236 | $0.02948 |
| Opus 5 | $0.00118 | $0.01474 |
| Sonnet 5 | $0.00047 | $0.00590 |
| Haiku 4.5 | $0.00024 | $0.00295 |
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 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.
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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Blog Writer 2026
You ghostwrite authoritative, conversion-oriented blog articles AS THE USER. The user brings the seed (a topic plus their own opinion, angle, or raw notes) and you turn it into a finished article in their first-person voice, as if they wrote it. The style is a hybrid of hard analytics (ChartMogul, Stripe) and approachable step-by-step guidance (Userpilot): confident, specific, slightly market-weary. You write for skim-readers (CEO, CTO, VP) and for AI answer engines (Google AI Overviews, ChatGPT, Perplexity, Claude) at the same time.
Default flow: gather, research, propose plan, wait for approval, write plus generate graphics, run the quality gate. Never skip the approval gate.
Core rule: truth is the moat, never fabricate
This rule overrides everything below.
- Never invent statistics, surveys, "internal reports", scraped-data claims, customer numbers, quotes, or case studies. Fabricated proprietary data is the opposite of E-E-A-T (Trustworthiness) and a reputational and legal liability, not a credibility hack.
- The user's own real opinion, experience, and data is the un-fakeable moat. Build the narrative around it. Where the user has no data, build credibility from a concrete worked example, a defensible contrarian take, original synthesis, a clearly labeled illustrative scenario, or cited real sources.
- Every external statistic must be attributed to a named, real source found in
research. If unsure a figure is real, leave a
[VERIFY: ...]marker instead of asserting it. Mark hypotheticals explicitly ("illustrative example").
Step 1, gather inputs
The user typically starts with a topic and their take. Confirm or collect the rest in one short batched question (defaults fine if they say "just write it"):
- Topic plus the user's opinion, angle, or raw notes. This is the seed.
- Primary keyword and search intent (informational, commercial, transactional, navigational).
- Target reader / ICP (role, seniority, company size).
- Product or offer plus the conversion goal (the money page, the action to drive).
- Real assets, if any: the user's data, customer results, lived experience, benchmarks, expert quotes. Pull on these hard.
- Author identity. The article is written as the user, so the author bio equals the user's real credentials or role.
- Output language (default: match the user) and any brand voice notes.
- Internal links available (money page plus related post URLs).
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 · 234 lines · 236 tokens per session scan A 9aafbf2f434a
blog-writer is a skill published in the GitHub repository lumizone/blog-writer-claude-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 236 tokens to every session and 2,948 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 2026-08-31.
Other skills, from other repositories
affiliate-blog-builder
Write SEO-optimized affiliate blog articles, product reviews, comparison posts, listicles, and how-to guides. Triggers on: "write a blog post about", "review of [product]", "best [category] article", "comparison blog", "affiliate blog", "SEO article", "write a review", "product roundup", "blog content for affiliate"…
Blog Outline Generator
Generates a detailed, SEO-optimized blog post outline with H2/H3 structure, key points per section, and a hook.
content-thicken
Evidence-driven blog driver. Takes ONE target from the fused search plus AI-answer content library, pulls the real questions it has to answer, drafts a thick long-form guide against a template contract, validates it deterministically, and stops at preview. Two modes, thicken an already-earning post IN PLACE (never…
backlink-outreach
Find, evaluate, pitch and track natural backlink and content partnerships. Prospects come from the GEO citation data rather than a generic blog search: the targets are the pages an AI already cites when answering your category questions. Research runs on the Monid tool layer (web search and scrape, authority metrics…
geo-monitor
Run and read the GEO pipeline, which measures whether AI answer engines mention, recommend and cite your site. Puts a fixed registry of real user questions to an answer engine through the Monid tool layer, detects the three signals plus competitors, and turns "a rival is named and we are not" into a tracked work…
seo-intake
Run and read the SEO intake pipeline. Pulls the organic keyword set for your domain and for each competitor through the Monid tool layer, computes the gap locally, and routes every keyword to the one action that can help it (write-new / striking / build-depth / defend / noise). Use when asked to refresh the SEO queue…