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 san-npm/skills-ws --skill blog-enginegit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/blog-engine)<a href="https://agentmods.dev/skills/san-npm/skills-ws/blog-engine"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/blog-engine/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/san-npm/skills-ws/blog-engine"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/blog-engine.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 | $0.00082 | $0.06639 |
| Opus 5 | $0.00041 | $0.03320 |
| Sonnet 5 | $0.00016 | $0.01328 |
| Haiku 4.5 | $0.00008 | $0.00664 |
Grade A, and why
blog-engine 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blog Engine
Production pipeline for one excellent long-form post, from blank page to publish-ready and through its first refresh. This skill owns execution of a single article. It deliberately does not re-derive program strategy or engine internals — cross-link instead:
- Topic clusters, editorial calendar, pillar/cluster model →
content-strategy - Template/directory/comparison pages generated at scale →
programmatic-seo - Engine-by-engine GEO stance, schema catalog, E-E-A-T, Core Web Vitals, hreflang →
seo-geo - Headline/CTA frameworks (PAS/AIDA/4U/BAB), voice calibration, before/after rewrites →
copywriting - Local intent (city/service pages, NAP, GBP) →
local-seo - Post-publish distribution sequences →
email-sequence,social-media-kit,social-media-growth
2026 ground rules (read first)
Search in mid-2026 is split between classic blue-link ranking and answer engines (Google AI Overviews & AI Mode, Bing Copilot, ChatGPT Search, Perplexity, Gemini, Claude). A post must work for both. Non-negotiables:
- Information gain over imitation. Copying the SERP's structure/word count produces derivative pages that Google's helpful-content systems and AI engines both ignore. Every post must add something the top results don't have: original data, a first-hand test, a named expert quote, a calculator, a decision table, or a clearer synthesis. Aim to be the source an answer engine quotes, not the tenth paraphrase.
- First-party experience (the extra "E"). Show you actually did the thing: screenshots you took, numbers you measured, a methodology paragraph, a dated byline with a real author bio and credentials. This is what separates a quotable post from spun content.
- Length follows intent, not a target. There is no minimum word count. A definition query deserves 600 focused words; a "best X for Y" comparison may need 3,000 with a table. Match the depth a satisfied reader needs and stop.
- Disclose AI assistance + keep an editorial gate. AI-drafted copy must be fact-checked, edited, and reviewed by a named human before publish. Add a transparency note in your content policy (e.g., "Drafted with AI assistance, reviewed and edited by [author]") where your jurisdiction or audience expects it. Mass-produced, unreviewed AI pages are the exact pattern Google's scaled-content-abuse policy (March 2024, enforced through 2026) demotes — see
programmatic-seofor the scale-safe variant. - Citation hygiene. Cite primary sources (the study, the docs, the filing — not a blog citing a blog). Record the publish/last-updated date of every source; drop or re-verify anything older than ~18 months for fast-moving topics. Never fabricate a statistic, quote, or study; if you can't verify it, cut it.
What ships with it
1 file 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 · 446 lines · 82 tokens per session scan A 907380a851e1
blog-engine is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 6,639 once invoked, about $0.0004 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
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…