aget-ask

aget-ask is a skill for Claude Code, Codex from aget-framework/aget. It costs 45 tokens per session (2,131 once invoked), scanned A, original, Apache-2.0.

A question-planning tool for clarifying what a user wants next. It treats clarifying questions as a way to reduce uncertainty and records how confident the agent was before asking.

In plain words
What is it for?
Use it to generate a small set of high-value questions about the desired approach, what should change, the scope, and the level of commitment.
Why use it?
It helps avoid acting on the wrong interpretation while avoiding unnecessary questions when the intended task is already reasonably clear.

Skill for Claude CodeCodex

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 skills/aget-framework/aget/aget-ask
Any agent
npx skills add aget-framework/aget --skill aget-ask
Clone the repo
git clone --depth 1 https://github.com/aget-framework/aget

Made for: Claude Code, Codex.

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 aget-ask

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/aget/aget-ask.svg)](https://agentmods.dev/skills/aget-framework/aget/aget-ask)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/aget/aget-ask"><img src="https://agentmods.dev/badge/skills/aget-framework/aget/aget-ask.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,131 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 $0.00045 $0.02131
Opus 5 $0.00023 $0.01066
Sonnet 5 $0.00009 $0.00426
Haiku 4.5 $0.00005 $0.00213

Measured 5d ago against content hash 3c9c65b4dd2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aget-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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • aget-ask — 95% identical, 5 lines differ
.claude/skills/aget-ask/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aget-ask

Ask clarifying questions as a measurement instrument for next-action prediction. Default: --clarification.

Instructions

This skill formalizes asking clarifying questions as an entropy-reduction tool, not UX politeness. Quality is measured by pre/post confidence delta on the agent's top-1 interpretation of the principal's intent — not by thoroughness, count, or category coverage.

Clarification Mode (default: --clarification)

Generate 2-4 clarifying questions that maximally narrow the prediction distribution over what the principal wants next.

Execution:

  1. Pre-ask measurement: Record the agent's top-1 interpretation of the principal's intent + confidence (0.0-1.0).

  2. Entropy threshold check: If confidence ≥ 0.70, proceed with best-guess + verify instead of asking. If < 0.70, continue.

  3. Generate candidates: Produce 4-8 candidate questions covering:

    • Frame-choice (which model/framing applies)
    • Replace-or-layer (affects which existing artifacts get modified)
    • Scope boundary (what's in/out for this turn)
    • Decision type (commitment level)
  4. Filter decorative / context-answerable:

    • Drop questions answerable from memory or KB context
    • Drop wordsmithing between near-equivalent options
    • Drop questions self-labeled "deferrable" in the draft
  5. Rank by load-bearing weight: Estimate how much each question's answer would change the next action. Higher = ranked earlier.

  6. Cap at 2-4: Top 2-4 questions only. If the problem genuinely needs 5+, the input had structural ambiguity — consider re-scoping the request instead of adding questions.

  7. Order strictly by descending load-bearing weight, NOT by category altitude. If your draft contains phrases like "hiding at the bottom", "biggest shape-determining", or "flag for alignment" attached to a non-first question, reorder before presenting.

  8. Present: Numbered questions with 2-3 concrete option examples per question to make answering cheap.

Read the full file on GitHub · 165 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. 5d ago First seen · 165 lines · 45 tokens per session scan A 3c9c65b4dd2c

Subscribe to this mod's changes

aget-ask is a skill published in the GitHub repository aget-framework/aget (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,131 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 2026-08-30.