Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/manthanpatelll/seo-blog-writer-claude-codenpx agentmods add skills/manthanpatelll/seo-blog-writer-claude-code/blog-writerWrote 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/manthanpatelll/seo-blog-writer-claude-code/blog-writer)<a href="https://agentmods.dev/skills/manthanpatelll/seo-blog-writer-claude-code/blog-writer"><img src="https://agentmods.dev/badge/skills/manthanpatelll/seo-blog-writer-claude-code/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/manthanpatelll/seo-blog-writer-claude-code/blog-writer"><img src="https://agentmods.dev/badge/skills/manthanpatelll/seo-blog-writer-claude-code/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 | $0.00126 | $0.02396 |
| Opus 5 | $0.00063 | $0.01198 |
| Sonnet 5 | $0.00025 | $0.00479 |
| Haiku 4.5 | $0.00013 | $0.00240 |
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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Blog Writer (next-article writer)
One call = the next pending topic in your queue, researched, written, and uploaded to WordPress as a draft, with the queue updated. You review the draft in WordPress and publish it yourself. Nothing goes live automatically.
This skill is the orchestrator. It chains:
- The queue —
seo-queue.json(your to-do list + progress tracker; start fromexamples/seo-queue.example.json) - The writing rules — the
geo-article-writerskill (skills/geo-article-writer/SKILL.md) - The publisher —
scripts/wp-publish.mjs(markdown -> WordPress draft) - (optional) The featured image generator —
scripts/gen-featured-image.mjs
This is the generalized version of the skill Manthan (@LeadGenMan) uses to run the TiltIt blog on autopilot. TiltIt is kept as the worked example throughout. Swap in your own brand by editing
seo-queue.jsonand the brand context block ingeo-article-writer/SKILL.md.
STEP -1 — FIRST-RUN ONBOARDING (do this BEFORE anything else, exactly once)
This skill ships pre-filled with TiltIt, which is Manthan's product. The very first time anyone runs this skill in a fresh clone, you MUST stop and re-brand it to the user's own product before writing a single article — otherwise their blog would talk about TiltIt.
How to detect a fresh, un-branded install: the string TiltIt still appears in skills/geo-article-writer/SKILL.md AND there is no .seo-blog-writer-onboarded marker file in the project root. If both are true, run onboarding first.
Onboarding (ask the user these, in one short message, then act):
- "This skill is currently set up for TiltIt (Manthan's product, https://tiltit.video). What's your brand name and website?"
- "One line: what is your product and how is it positioned? (e.g. pricing model, open-source or closed-source, who it's for.)"
- "What should I call the skill in your project? (default: keep
blog-writer— you can rename it to anything, e.g.acme-blog.)"
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 · 130 lines · 126 tokens per session scan A 506ab3dd67c5
blog-writer is a skill published in the GitHub repository manthanpatelll/seo-blog-writer-claude-code (16 stars, last pushed 2mo ago), licensed MIT. It adds 126 tokens to every session and 2,396 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…