publish-team-site

publish-team-site is a skill for Claude Code, Codex from ArchAstro/intern-mcp. It costs 47 tokens per session (332 once invoked), scanned A, original, MIT.

A guide for building or editing a private team website with Intern, such as a dashboard, launch room, specification or on-call page. Intern is a service for publishing these team-facing pages.

In plain words
What is it for?
Use it to create or revise team pages, add readable content and interactions, handle revisions, and invite people only when requested.
Why use it?
It provides rules for using the user's material, keeping pages private by default, and updating existing pages without overwriting newer edits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create or revise team pages, add readable content and interactions, handle revisions, and invite people only when requested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/archastro/intern-mcp/publish-team-site
Install

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.

Any agent
npx skills add ArchAstro/intern-mcp --skill publish-team-site
Clone the repo
git clone --depth 1 https://github.com/ArchAstro/intern-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for publish-team-site

README.md
[![agentmods](https://agentmods.dev/badge/skills/archastro/intern-mcp/publish-team-site/github.svg)](https://agentmods.dev/skills/archastro/intern-mcp/publish-team-site)
Your own site
<a href="https://agentmods.dev/skills/archastro/intern-mcp/publish-team-site"><img src="https://agentmods.dev/badge/skills/archastro/intern-mcp/publish-team-site/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.

agentmods 80×15 button for publish-team-site

Your own site · 80×15
<a href="https://agentmods.dev/skills/archastro/intern-mcp/publish-team-site"><img src="https://agentmods.dev/badge/skills/archastro/intern-mcp/publish-team-site.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00332
Opus 5 $0.00023 $0.00166
Sonnet 5 $0.00009 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured 4d ago against content hash 5a9d28e884aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

publish-team-site 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 4d 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.

skills/publish-team-site/SKILL.md · 27 lines

What it actually says

Publish a team site

Use the hosted Intern MCP connection. Honor the user's choice of destination.

If the user asks what Intern can do, offer to build a sample immediately: “I can build you a launch room with sample milestones so you can try it. Want me to make one?” Wait for acceptance before creating it. Installation alone does not authorize creation.

For a concrete request, use the material already in the conversation. Ask only for missing information essential to the result. Never invent company facts or present sample data as live.

Read the Intern authoring guide before using plugins. Build a complete first version with intern_create_site and initialSource. Prefer a useful private page with readable mobile layout, relevant content, and working interactions. An existing slug is a separate edit: fetch its latest source and apply against the returned revision.

Leave the site private unless the user asks otherwise. Invite people only when requested. Do not connect additional data sources without authorization.

Treat tool responses as authoritative:

  • Provisioning pending: explain briefly and follow the supplied retry instructions.
  • Publication failed: explain the failure and recover from the returned durable site state.
  • Publication succeeded: return the URL first, a short description, and one relevant optional next step.

Never claim a page is published before publication.state is published. If updating, confirm the successful revision response before claiming the edit is live.

Changes

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.

  1. 4d ago First seen · 27 lines · 47 tokens per session scan A 5a9d28e884aa

Subscribe to this mod's changes

publish-team-site is a skill published in the GitHub repository ArchAstro/intern-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 332 once invoked, about $0.0002 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 2026-09-09.