ask

ask is a command for coding agents from jonghklee/teammate-mcp. It costs 41 tokens per session (526 once invoked), scanned A, original, MIT.

A command for sending a question to another registered coding-agent workspace or terminal pane.

In plain words
What is it for?
Use it to ask another agent for information, delegate a check, or request help asynchronously; synchronous waiting is available when an immediate reply is required.
Why use it?
It lets agents pass work or questions to teammates without blocking the current session by default.

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/jonghklee/teammate-mcp/ask
Clone the repo
git clone --depth 1 https://github.com/jonghklee/teammate-mcp

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 ask

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonghklee/teammate-mcp/ask.svg)](https://agentmods.dev/commands/jonghklee/teammate-mcp/ask)
Your own site
<a href="https://agentmods.dev/commands/jonghklee/teammate-mcp/ask"><img src="https://agentmods.dev/badge/commands/jonghklee/teammate-mcp/ask.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 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 $0.00041 $0.00526
Opus 5 $0.00020 $0.00263
Sonnet 5 $0.00008 $0.00105
Haiku 4.5 $0.00004 $0.00053

Measured 4d ago against content hash d42c8f363165, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

commands/ask.md · 46 lines

What it actually says

Parse the slash arguments. The first non-flag token is the target label (e.g. claude1, codex1, worker). Everything after it is the question, taken verbatim.

As of v0.8.0 the default is ASYNC (mailbox / file-only delivery). The caller is never blocked, and the target's compose box / interactive bash / permission prompts are never corrupted by injected keystrokes.

Supported flags (anywhere in the args):

  • --wait: legacy SYNC mode — inject keystrokes + poll the target's screen for a completion marker. Use only when the caller cannot proceed without the inline reply. Will MERGE with text the user is mid-typing in the target compose box, so prefer the default.
  • --async / --no-wait: explicit async (default; included for clarity).
  • --timeout N: sync timeout in seconds (default 300; ignored when async).

Run this exact Bash command — do NOT call mcp__teammate__ask, which is the whole point of this slash command. The MCP tool path incurs:

  • a deferred-schema ToolSearch round-trip on the first call per session (1–3 s),
  • LLM extended-thinking time deciding to route to the tool (10–40 s on Opus with thinking enabled).

The CLI bypasses both:

teammate-mcp ask <LABEL> "<QUESTION>"          # async (default)
teammate-mcp ask --wait <LABEL> "<QUESTION>"   # legacy sync

Substitute <LABEL> and <QUESTION>; escape any literal " inside the question as \". If teammate-mcp is not on PATH, fall back to the absolute venv path (<repo>/.venv/bin/teammate-mcp).

Print the command's stdout back to the user verbatim, then end the turn. Do not summarise, do not add commentary, do not call any other tool.

If the user did not supply both a label and a question, print: Usage: /ask [--async] <label> <question...> and end the turn.

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. 4d ago First seen · 46 lines · 41 tokens per session scan A d42c8f363165

Subscribe to this mod's changes

ask is a command published in the GitHub repository jonghklee/teammate-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 526 once invoked, about $0.0002 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 2026-08-31.