dashboard-ask

dashboard-ask is a command for coding agents from wildware-uk/agent-dashboard. It costs 15 tokens per session (279 once invoked), scanned A, original, MIT.

Stop and ask the dashboard owner a question, then wait for the answer.

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-ask
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-ask

README.md
[![agentmods](https://agentmods.dev/badge/commands/wildware-uk/agent-dashboard/dashboard-ask.svg)](https://agentmods.dev/commands/wildware-uk/agent-dashboard/dashboard-ask)
Your own site
<a href="https://agentmods.dev/commands/wildware-uk/agent-dashboard/dashboard-ask"><img src="https://agentmods.dev/badge/commands/wildware-uk/agent-dashboard/dashboard-ask.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 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 $0.00015 $0.00279
Opus 5 $0.00008 $0.00139
Sonnet 5 $0.00003 $0.00056
Haiku 4.5 $0.00002 $0.00028

Measured today against content hash 336633f1d5ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dashboard-ask 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-ask.md · 30 lines

What it actually says

Ask the owner: $ARGUMENTS

Pick the kind by what you need back, and do not use text where a real control would do:

  • a value → text
  • permission for one consequential thing → confirm
  • one action out of several → buttons
  • one item from a list → choice
  • several → multi_choice
  • something you drafted and are about to send → form, with your draft in default, your actions in options, and the field named by label

Phrase question so it is answerable without reading my transcript, and put the context in detail. Pass project so the banner says what this is about.

Then wait properly: while the state comes back pending, keep calling await_request with the request_id. Stop only on answered, timeout or cancelled.

timeout and cancelled are not permission. If either comes back, do not do the thing — post an update saying you are blocked, and tell me.

For a form, act on value.text, not on the draft you sent.

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 · 15 tokens per session scan A 336633f1d5ad

Subscribe to this mod's changes

dashboard-ask is a command published in the GitHub repository wildware-uk/agent-dashboard (0 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 279 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.