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 METAXGTSEOSEM/Awesome-post-skills --skill b2b-product-page-writergit clone --depth 1 https://github.com/METAXGTSEOSEM/Awesome-post-skillsWrote 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/metaxgtseosem/awesome-post-skills/b2b-product-page-writer)<a href="https://agentmods.dev/skills/metaxgtseosem/awesome-post-skills/b2b-product-page-writer"><img src="https://agentmods.dev/badge/skills/metaxgtseosem/awesome-post-skills/b2b-product-page-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/metaxgtseosem/awesome-post-skills/b2b-product-page-writer"><img src="https://agentmods.dev/badge/skills/metaxgtseosem/awesome-post-skills/b2b-product-page-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 | $0.00119 | $0.04426 |
| Opus 5 | $0.00060 | $0.02213 |
| Sonnet 5 | $0.00024 | $0.00885 |
| Haiku 4.5 | $0.00012 | $0.00443 |
Grade A, and why
b2b-product-page-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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 12d ago First seen · 349 lines · 119 tokens per session scan A 7af5de9b8864
b2b-product-page-writer is a skill published in the GitHub repository METAXGTSEOSEM/Awesome-post-skills (1 stars, last pushed 2mo ago), with no licence file. It adds 119 tokens to every session and 4,426 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 2026-08-31.
Other skills, from other repositories
startup-marketing-playbook
Marketing playbook for bootstrapped startups with zero budget. Covers organic-only channels including SEO, community building, social media, and word-of-mouth tactics that cost nothing but time. Follow @WeiYipei on X.
linkedin-cold-reviver
Detect a going-cold lead and fire one completely new angle that lands value whether or not they reply. Use when a thread has gone quiet and a re-ask would only nag.
linkedin-comment-engine
Draft two authority-building comments to leave on someone else's post, warming through visibility instead of DMs. Use when you want a decision-maker to notice you and click your profile.
linkedin-engage-plan
Design a multi-touch warming sequence for one target so they recognise you before you ever message them. Use when you have a specific person worth warming up before any pitch.
linkedin-engager-analytics
Analyse everyone who liked or commented on a post, score them against your ICP, and return the match rate plus the top 10 profiles with a real-signal outreach note for each. Use after a post lands to find the warm prospects hiding in your engagement.
linkedin-followup-adapter
Write the next follow-up from where the conversation actually is, off the real state of the thread rather than a fixed timer. Use when a prospect has gone quiet and the next touch needs a new angle.