dashboard-check

dashboard-check is a command for coding agents from wildware-uk/agent-dashboard. It costs 19 tokens per session (342 once invoked), scanned A, original, MIT.

Verify the Agent Dashboard plugin is configured and reachable, and say exactly what is wrong if not.

Command

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.

agentmods
npx agentmods add commands/wildware-uk/agent-dashboard/dashboard-check
Clone the repo
git clone --depth 1 https://github.com/wildware-uk/agent-dashboard

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-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/wildware-uk/agent-dashboard/dashboard-check.svg)](https://agentmods.dev/commands/wildware-uk/agent-dashboard/dashboard-check)
Your own site
<a href="https://agentmods.dev/commands/wildware-uk/agent-dashboard/dashboard-check"><img src="https://agentmods.dev/badge/commands/wildware-uk/agent-dashboard/dashboard-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00019 $0.00342
Opus 5 $0.00010 $0.00171
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured today against content hash cfda98536f3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashboard-check 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 today.

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.

plugins/agent-dashboard/commands/dashboard-check.md · 30 lines

What it actually says

Check the dashboard connection end to end and report each step.

  1. Tools present. Are the agent-dashboard MCP tools available in this session? If not, the plugin is installed but not configured or not enabled — the dashboard_url and agent_token come from /plugin and there is nothing to guess.
  2. The server answers you. Call list_projects(). Interpret the failure rather than repeating it:
    • HTTP 401 → the token is missing, malformed or revoked. It has to be re-minted on the deployment with agent-dashboard mint-token <name>; it cannot be recovered.
    • a connection failure → dashboard_url is wrong, or the deployment is not reachable from this machine. It must be the origin only, with no trailing slash and no /mcp.
    • HTTP 429 → it is reachable and you are just being rate limited. That is a pass.
  3. The channel. Is agent-dashboard-channel loaded in this session? If the tools work but the channel is absent, the session was started without --dangerously-load-development-channels plugin:agent-dashboard@agent-dashboard. Everything still works; replies just arrive on your next heartbeat instead of instantly. Say that rather than reporting it as broken.

Report a short verdict per step and, if anything failed, the one command or setting that fixes it.

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. today First seen · 30 lines · 19 tokens per session scan A cfda98536f3d

Subscribe to this mod's changes

dashboard-check is a command published in the GitHub repository wildware-uk/agent-dashboard (0 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 342 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 2026-09-04.