ask-questions

ask-questions is a command for Claude Code from simonrowland/goal-flight. It costs 27 tokens per session (1,336 once invoked), scanned A, original, MIT.

A command that asks read-only workers to find unanswered questions before unattended coding work begins. It looks for unclear requirements, dependencies between work sections, and possible integration problems.

In plain words
What is it for?
Use it before or during a multi-step coding task to check the overall plan, a specific area such as authentication or a database migration, the current work section, or upcoming sections.
Why use it?
It surfaces issues that could otherwise stop a long automated run and require the user to answer questions midway through the work.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

Part of the goal-flight plugin — 10 skills, 17 commands, 3 hooks 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/simonrowland/goal-flight/ask-questions
Clone the repo
git clone --depth 1 https://github.com/simonrowland/goal-flight

Made for: Claude Code.

Or install goal-flight, the plugin that ships this one along with the rest of its 10 skills, 17 commands, 3 hooks.

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-questions

README.md
[![agentmods](https://agentmods.dev/badge/commands/simonrowland/goal-flight/ask-questions.svg)](https://agentmods.dev/commands/simonrowland/goal-flight/ask-questions)
Your own site
<a href="https://agentmods.dev/commands/simonrowland/goal-flight/ask-questions"><img src="https://agentmods.dev/badge/commands/simonrowland/goal-flight/ask-questions.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,336 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 5.1 $0.00027 $0.01336
Opus 5 $0.00014 $0.00668
Sonnet 5 $0.00005 $0.00267
Haiku 4.5 $0.00003 $0.00134

Measured yesterday against content hash d561d8cf93bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ask-questions 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 yesterday.

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-questions.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ask-questions [--scope ]

Read:

  • protocols/dispatch-routing.md

Spawn read-only workers to anticipate integration / requirements / snags questions. Surface only the ones with enough context to make sense to the user. Goal: clear ambiguities up front so the 12-hour unattended run doesn't stall on user input.

Modes

  • Standalone: /goal-flight ask-questions — user invokes explicitly between decompose-plan and execute (or any time).
  • Auto-chained: invoked at the end of decompose-plan with --scope decomposition.
  • Continuous: invoked from inside execute when the orchestrator hits an ambiguity that requires user input.

Steps

1. Pick scope

Scope arg Anticipator focus
decomposition (default after decompose-plan) Cross-chunk dependencies, ambiguous SCOPE/ACCEPTANCE wording, missing FORBIDDEN constraints
<area> (e.g., auth, db-migration) Area-specific chunks; ignore unrelated work
current-chunk (continuous mode) The chunk currently being executed; surface only blockers
next-chunks (continuous mode, look-ahead) Next 1-2 upcoming chunks; non-blocking surfacing

2. Spawn 1-2 anticipatory workers

Use read-only explorer workers through the host delegate operation with the prompt at prompts/ask-anticipatory.md (current Claude wrapper: Explore subagents; other hosts: adapter delegate equivalent). Substitute the scope and paths. Each worker:

  1. Scans the goal-queue, AGENTS.md, any binding-spec, recent git log.
  2. Generates (question, default-answer, confidence, risk-if-wrong, second-opinion-suggestion) tuples.
  3. For low-confidence items: notes "consider second opinion from <other ready, concern-diverse reviewer>" — for example, if the orchestrator's primary model is Claude in the current wrapper, use a codex/cursor/grok peer; if the orchestrator is codex, use a Claude-compatible/cursor/grok peer.

If two workers are spawned (recommended for decomposition scope; one is sufficient for current-chunk), run in parallel and dedupe results.

Read the full file on GitHub · 101 lines

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. yesterday Changed · +2 lines · +16 tokens per session d561d8cf93bd
  2. 6d ago First seen · 99 lines · 11 tokens per session scan A 856525c1d3be

Subscribe to this mod's changes

ask-questions is a command published in the GitHub repository simonrowland/goal-flight (20 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,336 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.