dashboard-offline

dashboard-offline is a command for coding agents from wildware-uk/agent-dashboard. It costs 14 tokens per session (204 once invoked), scanned A, original, MIT.

A command for closing an Agent Dashboard session after work finishes or stops. It posts a final summary, completes finished tasks, and ends the session.

In plain words
What is it for?
Summarising completed and incomplete work, closing claimed tasks appropriately, and ending a dashboard session.
Why use it?
It prevents the owner from seeing a run as still active and makes unfinished work or unanswered questions explicit.

Command

Part of the agent-dashboard plugin — 5 skills, 6 commands, 1 hook, 2 MCP servers shipped together

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-offline
Clone the repo
git clone --depth 1 https://github.com/wildware-uk/agent-dashboard

Or install agent-dashboard, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 1 hook, 2 MCP servers.

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-offline

README.md
[![agentmods](https://agentmods.dev/badge/commands/wildware-uk/agent-dashboard/dashboard-offline.svg)](https://agentmods.dev/commands/wildware-uk/agent-dashboard/dashboard-offline)
Your own site
<a href="https://agentmods.dev/commands/wildware-uk/agent-dashboard/dashboard-offline"><img src="https://agentmods.dev/badge/commands/wildware-uk/agent-dashboard/dashboard-offline.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00204
Opus 5 $0.00007 $0.00102
Sonnet 5 $0.00003 $0.00041
Haiku 4.5 $0.00001 $0.00020

Measured today against content hash ec880094adb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashboard-offline 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-offline.md · 20 lines

What it actually says

Wind down on the dashboard.

  1. Post a final post_update — what got done, what did not, and anything left for the owner to pick up. success if the run finished what it set out to do, warn if it stopped short.
  2. If you claimed tasks that are actually finished, complete_task them. If you claimed tasks you did not finish, say so in the update and leave them claimed rather than closing them falsely.
  3. If you have a request_input still outstanding, tell me — do not end the session on top of a question the owner may still answer.
  4. end_session({ session_id }). Idempotent, so it is safe if you are unsure whether it already ran.

Without step 4 the owner's presence list shows a session that looks alive and is not.

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 · 20 lines · 14 tokens per session scan A ec880094adb4

Subscribe to this mod's changes

dashboard-offline is a command published in the GitHub repository wildware-uk/agent-dashboard (0 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 204 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.