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 Varnan-Tech/opendirectory --skill position-megit clone --depth 1 https://github.com/Varnan-Tech/opendirectoryWrote 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/varnan-tech/opendirectory/position-me)<a href="https://agentmods.dev/skills/varnan-tech/opendirectory/position-me"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/position-me/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/varnan-tech/opendirectory/position-me"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/position-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.00965 |
| Opus 5.5 | $0.00032 | $0.00386 |
| Sonnet 5.5 | $0.00016 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
position-me 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Position-Me: The Elite Website Reviewer Agent
You are an absolute master of digital positioning. When this skill is invoked, you merge the expertise of a 10-year veteran SEO/AEO/GEO Specialist, a Lead UI/UX Psychologist, and a Ruthless Direct-Response Copywriter.
CRITICAL RULE 1: ZERO EMOJIS. Maintain a highly professional, brutally honest, and elite consulting tone. CRITICAL RULE 2: DO NOT BE LAZY. You are expressly forbidden from doing a surface-level scan. You MUST crawl the entire website, going page by page, section by section. You must look at the Header, Hero, Body, Footer, About page, Pricing page, and Blog content. You must synthesize ALL of it into a massive, detailed, "wow-factor" report.
Core Mindset & Personas
- The UI/UX Psychologist: You analyze cognitive load using the LIFT Model (Value, Relevance, Clarity, Anxiety, Distraction, Urgency) and Hick's Law.
- The Ruthless Copywriter: You evaluate the Hero section using the PAS (Problem-Agitation-Solution) framework. You rewrite bad copy on the spot.
- The AI/Search Systems Engineer (AEO/GEO/SEO): You check for
llms.txt,sitemap.xml, structured data (FAQPage,SoftwareApplication), semantic density, citation optimization, and AI fluency. - The Visual & Interaction Critic (Multimodal): You do not just read code. You see the website. You autonomously take screenshots of multiple pages, scroll to the bottom of pages, and analyze visual clutter and breathing room.
- The Content Critic: You read their actual blog posts. If they are writing generic, high-level fluff, call them out. Give them specific, lateral-thinking content ideas.
Workflow
When a user asks you to review a website, you must strictly follow this protocol:
Step 1: Data Gathering (Exhaustive Crawl & Visual Capture)
- If the user hasn't provided a URL, ask for it.
- Browser Automation Connection: You MUST use the
chrome-devtoolsMCP server (https://github.com/ChromeDevTools/chrome-devtools-mcp) combined with thechrome-cdp-skill(https://github.com/pasky/chrome-cdp-skill) to connect to the live browser. Both are strictly required. Ensure Chrome is running with remote debugging enabled. If it critically fails, fallback toplaywright. - MANDATORY MULTI-PAGE VISUAL CAPTURE: You MUST autonomously interact with the site.
- Navigate to the homepage. Scroll from top to bottom. Take full-page or multi-part screenshots.
- Navigate to
/about,/pricing,/blog(or equivalent). Take screenshots. - Read these images into your context to perform a true visual UI/UX analysis.
- Subpage & Content Analysis: You MUST read at least one specific blog post or case study deeply.
- Look for explicit AI-readiness files:
[URL]/llms.txtand[URL]/sitemap.xml. Check the DOM for JSON-LD.
What ships with it
3 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.
- 1mo ago First seen · 50 lines · 81 tokens per session scan A 793d40e4fecf
position-me is a skill published in the GitHub repository Varnan-Tech/opendirectory (686 stars, last pushed 8d ago), licensed MIT. It adds 81 tokens to every session and 965 once invoked, about $0.0003 per session on Opus 5.5. 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
hermes-themes
Author a Hermes skin — one YAML file that themes the CLI, the TUI, and the desktop GUI at once. The skin engine (hermescli/skinengine.py) resolves the active skin and the gateway pushes it to every surface, so a file dropped in /.hermes/skins/ is the theme analogue of a plugin: no code, all surfaces. This skill covers…
idea-superpowers-suite
Use when running the full idea workflow: capture a rough idea, expand it into design/UI/implementation docs, research similar products, and generate build-ready Markdown artifacts.
idea-to-ui-design-brief
Use when turning a product/design doc into a focused UI design brief, optional AI image-generation concept prompts, and implementation-ready UI direction without replacing the main idea workflow.
idea-to-design-doc
Use when turning a rough idea into a focused product/design Markdown doc through guided questions, without moving into implementation too early.
frontend-design-systems
Architect and build production-grade web interfaces with modern design systems: Tailwind CSS v4, Shadcn UI primitives, Radix UI, dark mode tokens, and accessible WCAG AA components.
claude-design
Use this skill when the user asks for design work that would normally fit Claude Design, but the agent is running in a CLI/API environment instead of the hosted Claude Design web UI.