dashboard

dashboard is a command for Claude Code from ChainGPT-org/chaingpt-claude-skill. It costs 21 tokens per session (316 once invoked), scanned A, original, MIT.

A local, read-only web dashboard for viewing the ChainGPT marketplace. It includes pages for an overview, skills, activity, health, and information about the dashboard.

In plain words
What is it for?
It is for opening the marketplace dashboard on a local port and receiving its temporary access token. It can display the local URL, token, and token-file location, but it does not describe tools for changing marketplace data.
Why use it?
It gives the user a browser view of marketplace information without allowing signing flows through the browser. The dashboard runs only on the user's own computer.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the chaingpt plugin — 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server shipped together

Good fit It is for opening the marketplace dashboard on a local port and receiving its temporary access token. It can display the local URL, token, and token-file location, but it does not describe tools for changing marketplace data.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/chaingpt-org/chaingpt-claude-skill/dashboard
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.

Clone the repo
git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

Made for: Claude Code.

Or install chaingpt, the plugin that ships this one along with the rest of its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server.

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 dashboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/chaingpt-org/chaingpt-claude-skill/dashboard.svg)](https://agentmods.dev/commands/chaingpt-org/chaingpt-claude-skill/dashboard)
Your own site
<a href="https://agentmods.dev/commands/chaingpt-org/chaingpt-claude-skill/dashboard"><img src="https://agentmods.dev/badge/commands/chaingpt-org/chaingpt-claude-skill/dashboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 316 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 $0.00021 $0.00316
Opus 5 $0.00010 $0.00158
Sonnet 5 $0.00004 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured 8d ago against content hash 3a85b3500dc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dashboard 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 8d 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.

.claude-plugin/commands/dashboard.md · 20 lines

What it actually says

Open the ChainGPT marketplace dashboard for the user.

Steps:

  1. Call the MCP tool chaingpt_dashboard_serve. If the user passed a port as $1, pass it as { "port": <number> }; otherwise call with no args (default port 8788).
  2. The tool will print a URL (http://127.0.0.1:<port>), a freshly rotated admin token, and the token-file path. Surface all three to the user, formatted clearly, in your reply.
  3. After the URL + token, offer to open the URL in their default browser using open <url> on macOS or xdg-open <url> on Linux. Wait for the user to confirm before running the command — do NOT auto-open.
  4. Remind the user once that the dashboard binds 127.0.0.1 only, the admin token rotates each time /chaingpt:dashboard is invoked, and the dashboard is read-only (no signing flows are proxied through the browser).

Do not:

  • Do not attempt to fetch or display dashboard content yourself — the user is the one with the browser.
  • Do not store the admin token in any file other than the path the tool already wrote it to.
  • Do not run the dashboard on a non-loopback bind (the tool will refuse anyway).
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. 8d ago First seen · 20 lines · 21 tokens per session scan A 3a85b3500dc8

Subscribe to this mod's changes

dashboard is a command published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (16 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 316 once invoked, about $0.0001 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.