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/keepYaoung/artifact-organizernpx agentmods add skills/keepyaoung/artifact-organizer/artifact-organizer-shareWrote 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/keepyaoung/artifact-organizer/artifact-organizer-share)<a href="https://agentmods.dev/skills/keepyaoung/artifact-organizer/artifact-organizer-share"><img src="https://agentmods.dev/badge/skills/keepyaoung/artifact-organizer/artifact-organizer-share/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/keepyaoung/artifact-organizer/artifact-organizer-share"><img src="https://agentmods.dev/badge/skills/keepyaoung/artifact-organizer/artifact-organizer-share.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 | $0.00083 | $0.00888 |
| Opus 5.5 | $0.00033 | $0.00355 |
| Sonnet 5.5 | $0.00017 | $0.00178 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
artifact-organizer-share 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 2mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact Organizer — Share mode
Deploys an existing .html file (typically from ~/.artifact-organizer/out/) to Vercel and returns a public URL. Thin wrapper over the artifact-organizer skill's scripts/share.sh.
When to use
- User just rendered a Artifact Organizer page and says "share this", "send me a link", "can I send this to someone".
- User explicitly asks to deploy an HTML file.
- User wants a public URL for an existing output.
Do not use for: generating new pages (use hyperscribe or hyperscribe-slides), deploying arbitrary sites (this only handles Artifact Organizer outputs).
Preconditions
vercelCLI must be on PATH. If missing, the script exits 127 and tells the user:npm i -g vercel && vercel login.- An
.htmlfile must exist at the path you pass. - User should have run
vercel loginat least once (interactive — don't try to do it yourself).
Resolve the HTML path
- Explicit path given — use it (verify it exists).
- "last" / "just now" / no path — find the most recent output:
If nothing exists, ask the user to render one first withHTML=$(ls -1t ~/.artifact-organizer/out/*.html 2>/dev/null | head -1)hyperscribe/hyperscribe-slides/hyperscribe-diff.
Deploy
# Locate the share script (installed alongside the hyperscribe skill).
SHARE=$(for p in \
./.claude/skills/artifact-organizer ~/.claude/skills/artifact-organizer \
./.codex/skills/artifact-organizer ~/.codex/skills/artifact-organizer \
./.cursor/skills/artifact-organizer ~/.cursor/skills/artifact-organizer \
./.opencode/skills/artifact-organizer ~/.opencode/skills/artifact-organizer \
~/.claude/plugins/cache/artifact-organizer-marketplace/*/plugins/artifact-organizer
do [ -f "$p/scripts/share.sh" ] && { echo "$p/scripts/share.sh"; break; }; done)
if [ -z "$SHARE" ]; then
echo "artifact-organizer share script not found. Install with: npx skills add keepYaoung/artifact-organizer" >&2
exit 1
fi
bash "$SHARE" "$HTML"
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.
- 2mo ago First seen · 80 lines · 83 tokens per session scan A 4e591a1e1b6e
artifact-organizer-share is a skill published in the GitHub repository keepYaoung/artifact-organizer (2 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 888 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 2026-08-31.
Other skills, from other repositories
agui-tauri-windows-signing
Configure and troubleshoot Authenticode code signing for Tauri Windows builds (.exe / .msi) using the AG-UI organization's DigiCert code-signing certificate stored in Azure Key Vault (non-exportable RSA-HSM key), signed via AzureSignTool authenticated with GitHub OIDC. Covers tauri.conf.json signCommand wiring, the CI…
all-deploy
Deploys websites, web apps, APIs, and agents to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Handles plain HTML/CSS/JS pages and static sites (Astro, Hugo, Jekyll, Eleventy, Vite) as well as Next, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP servers, Claude Agent SDK…
mdma-integration
Integrate MDMA into an application and build features with it — wire up parsing, the runtime store, React rendering, LLM streaming, custom components, prompts, and CI validation. Use this skill when the user asks to add MDMA to an app, build a chat that streams MDMA, author or maintain a custom prompt, validate MDMA…
publish-website
Puts a web page on the internet for free, with no terminal and no paid plan — a folder of HTML/CSS/JS, or a page Claude just built. Checks the page for the things that silently break it once it's live (wrong filename, broken image paths, capitalisation that works on your computer and 404s on the host, API keys left in…
alibaba-maestro
Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents.…
contabo-live-instance-lifecycle-guard
Live-guard skill for Contabo VPS and VDS lifecycle operations including instance creation with product selection and region, reinstallation with image and Cloud-Init userData, and cancellation. Requires mandatory contract period acknowledgment (1, 3, 6, or 12 months), billing impact confirmation, and a rollback plan…