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 just-done/just-publish-mcp --skill just-publishgit clone --depth 1 https://github.com/just-done/just-publish-mcpWrote 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/just-done/just-publish-mcp/just-publish)<a href="https://agentmods.dev/skills/just-done/just-publish-mcp/just-publish"><img src="https://agentmods.dev/badge/skills/just-done/just-publish-mcp/just-publish/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/just-done/just-publish-mcp/just-publish"><img src="https://agentmods.dev/badge/skills/just-done/just-publish-mcp/just-publish.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 | $0.00195 | $0.01393 |
| Opus 5.5 | $0.00078 | $0.00557 |
| Sonnet 5.5 | $0.00039 | $0.00279 |
| Haiku 4.5 | $0.00019 | $0.00139 |
Grade A, and why
just-publish 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Just Publish: put a static website online
Just Publish (https://justpublish.ai) turns static files into a live website at
https://{slug}.justpublish.site/. Publishing is free and there is no build
step: files in, working link out.
Connect and sign in
The MCP server is https://mcp.justpublish.ai/. In Claude it is the connector
at https://mcp.justpublish.ai/claude, added from the connector directory or
as a custom connector; in Claude Code it is one command:
claude mcp add --transport http just-publish https://mcp.justpublish.ai/claude
Cursor, VS Code, a CLI agent or any other MCP client adds
https://mcp.justpublish.ai/ instead. Either way the person signs in the first
time, with Google or a code sent to their email address. Authorization is
OAuth 2.1 and the client discovers what it needs from the server, so the
advanced client-id and client-secret fields stay empty.
Both addresses serve the same four tools: deploy, list_sites,
get_site_files and update_site_file. Every site is filed under the
signed-in account, which changes how you work:
deploytakes no email address. Do not ask the user for one.list_sitesreturns the sites that account has already published, so you can find a site instead of asking for an id the user does not have.get_site_filesandupdate_site_fileneed only asite_idfor that account's own sites.- Report the live
urland stop. The account is what makes the site theirs to find, change and take down later.
Step by step for people: https://justpublish.ai/docs/mcp/connect (Claude: https://justpublish.ai/docs/mcp/claude)
When to use this skill
The user says things like:
- "publish this site" / "put this online" / "make this a website"
- "give me a link for this" / "I want a URL I can share"
- "host what we just built"
- "update my site" (one published earlier with Just Publish)
The site must be static: HTML, CSS, JS, images, fonts. No server code, no SSR, no build step.
Do NOT use it when the user needs a backend (APIs, databases, Next.js or Nuxt SSR), wants to buy or manage a domain (that is a registrar's job), or wants to change a site that was not published with Just Publish.
What ships with it
4 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.
- 10d ago Changed · -34 lines 7306f942b2a2
- 1mo ago Changed · +51 lines · +40 tokens per session 78ae9d21560d
- 2mo ago First seen · 94 lines · 155 tokens per session scan A 018eca68594c
just-publish is a skill published in the GitHub repository just-done/just-publish-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 195 tokens to every session and 1,393 once invoked, about $0.0008 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
ssh-incident
A diagnosis order for "the server is down", "the site is slow", "something broke". Use when investigating a problem on a remote server through the ssh tools, before changing anything.
threebrowser-studio-mcp
Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, restricting node access with IP or origin allowlists, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack…
cdn-fallback
Put a 3x-ui inbound behind a CDN (WebSocket, gRPC or xhttp through Cloudflare) or share port 443 between several inbounds using Xray fallbacks. Use when REALITY is blocked or unsuitable, when the server IP must stay hidden behind a CDN, when a real domain and certificate are in play, or when several protocols need to…
multi-node
Attach, secure and operate additional 3x-ui panels as nodes of a master panel — probe before saving, choose a TLS trust mode (verify/skip/pin/mTLS), select which inbounds sync, and monitor health and per-node traffic. Use when asked to add a server to a cluster, set up mTLS between panels, work out which node is…
onplana-project-planner
Turn a goal or a brief into an executable Onplana plan over its MCP server: write a plan.md and attach it to the project, decompose it into tasks and subtasks, set start/due dates and dependencies, assign owners, add test cases as you go, and create tasks for the downstream surfaces a change ripples to. Use this…