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 ViryaZheng/recomby-geo --skill geo-review-htmlgit clone --depth 1 https://github.com/ViryaZheng/recomby-geoWrote 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/viryazheng/recomby-geo/geo-review-html)<a href="https://agentmods.dev/skills/viryazheng/recomby-geo/geo-review-html"><img src="https://agentmods.dev/badge/skills/viryazheng/recomby-geo/geo-review-html/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/viryazheng/recomby-geo/geo-review-html"><img src="https://agentmods.dev/badge/skills/viryazheng/recomby-geo/geo-review-html.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 | $0.00140 | $0.01332 |
| Opus 5 | $0.00070 | $0.00666 |
| Sonnet 5 | $0.00028 | $0.00266 |
| Haiku 4.5 | $0.00014 | $0.00133 |
Grade A, and why
geo-review-html 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
geo-review-html — interactive client-review HTML
The Markdown briefs/drafts are right for the GEO operator; they are awkward for the client side. This skill renders a companion HTML alongside the Markdown so non-technical reviewers can work in the browser. Battle-tested in the SEA-CICSIC 9-draft batch (see issue #1).
Division of labour (do not blur this):
- Interaction logic is fixed —
templates/review.htmlowns localStorage auto-save, JSON export, the progress counter, comment toggles, and the approve/return state machine. It is correct as written; do not regenerate it per run. - Visual layer is the template's CSS — that is where the vendored
frontend-designskill applies. When a client wants a branded or more distinctive look, restyle the<style>block oftemplates/review.htmlusingfrontend-designprinciples.--accentis already overridable per client viabrand_context(see below); deeper restyling edits the CSS. render_html.pyonly parses Markdown + meta into a payload and injects it.
When to use
04-content-briefStep 7 — emitbriefs/<id>.html(fill-form) next to the.md.04-content-briefStep 9 — ingest the reviewer's returned*.feedback.json.05-productionStep 7 — emitdrafts/<id>.html(review form) next to the.md.- Whenever a client folder's
briefs/index.htmlentry page needs (re)building.
Usage
SK=plugins/recomby-geo/skills/geo-review-html
# Flavor A — fill-form HTML for a brief with REQUIRED-FILL slots
python3 $SK/scripts/render_html.py --mode brief \
--md clients/<slug>/briefs/<id>.md \
--meta clients/<slug>/briefs/<id>.meta.json \
--brand clients/<slug>/brand_context.json \
--out clients/<slug>/briefs/<id>.html
# Flavor B — review HTML for a publish-ready draft (section comments + approve)
python3 $SK/scripts/render_html.py --mode draft \
--md clients/<slug>/drafts/<id>.md \
--meta clients/<slug>/drafts/<id>.meta.json \
--brand clients/<slug>/brand_context.json \
--out clients/<slug>/drafts/<id>.html
# Entry page — one card per brief/draft, live progress, status tags
python3 $SK/scripts/render_html.py --mode index \
--client-dir clients/<slug> \
--brand clients/<slug>/brand_context.json \
--out clients/<slug>/briefs/index.html
What ships with it
2 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.
- 12d ago First seen · 104 lines · 140 tokens per session scan A c012cdaded0c
geo-review-html is a skill published in the GitHub repository ViryaZheng/recomby-geo (454 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 1,332 once invoked, about $0.0007 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
web-browse
Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.
web-scraping-javascript-sites
Scrape TypeScript, React, Next.js, Nuxt, Vue SPA sites. Know when to use raw HTML fetch vs browser automation.
playwright
Use Playwright for browser automation, web scraping, form filling, screenshots, authenticated flows, and deployed-site verification.
agent-browser
Browser automation CLI built for AI agents - compact ref-based text output (200-400 tokens vs 3000-5000 for full DOM), native Rust, 50+ commands. Default browser-automation tool for the fleet. Use for any web navigation, scraping, form-filling, screenshots, or testing from the shell.
apple-platform-automation
Manage Apple/macOS personal apps and device workflows from Hermes, including Apple Notes, Reminders, Find My, iMessage/SMS, and UI automation. Use when a task involves Apple ecosystem data or macOS-only CLIs such as memo, remindctl, imsg, FindMy.app, AppleScript, or Peekaboo.
browser-use
Web scraping, screenshots, form filling, file downloads/uploads, Google/DuckDuckGo image search, YouTube video downloading, and TikTok video downloading.