core-ask-questions-if-underspecified

core-ask-questions-if-underspecified is a skill for Claude Code, Codex from oodaris/autocodex. It costs 20 tokens per session (398 once invoked), scanned A, original, MIT.

A skill that asks targeted questions when a coding request lacks important details or contains ambiguity.

In plain words
What is it for?
Use it before coding when requirements are incomplete, to identify missing inputs and confirm whether the work belongs in a command-line tool, API, or user interface.
Why use it?
It helps prevent work from starting without the required schemas, configuration examples, constraints, or success criteria.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before coding when requirements are incomplete, to identify missing inputs and confirm whether the work belongs in a command-line tool, API, or user interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oodaris/autocodex/core-ask-questions-if-underspecified
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.

Any agent
npx skills add oodaris/autocodex --skill core-ask-questions-if-underspecified
Clone the repo
git clone --depth 1 https://github.com/oodaris/autocodex

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 core-ask-questions-if-underspecified

README.md
[![agentmods](https://agentmods.dev/badge/skills/oodaris/autocodex/core-ask-questions-if-underspecified/github.svg)](https://agentmods.dev/skills/oodaris/autocodex/core-ask-questions-if-underspecified)
Your own site
<a href="https://agentmods.dev/skills/oodaris/autocodex/core-ask-questions-if-underspecified"><img src="https://agentmods.dev/badge/skills/oodaris/autocodex/core-ask-questions-if-underspecified/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for core-ask-questions-if-underspecified

Your own site · 80×15
<a href="https://agentmods.dev/skills/oodaris/autocodex/core-ask-questions-if-underspecified"><img src="https://agentmods.dev/badge/skills/oodaris/autocodex/core-ask-questions-if-underspecified.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00020 $0.00398
Opus 5 $0.00010 $0.00199
Sonnet 5 $0.00004 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 10d ago against content hash 5893d9d17e79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

core-ask-questions-if-underspecified 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 10d 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.

skills/core-ask-questions-if-underspecified/SKILL.md · 58 lines

What it actually says

Ask Questions If Underspecified

Repo anchors (autocodex)

  • CLI_PATH: cmd/autocodex/
  • INTERNAL_PATH: internal/
  • PLUGINS_PATH: plugins/
  • DOCS_PATH: docs/
  • SKILLS_PATH: skills/
  • UI_PATH: web/
  • TEST_COMMANDS
    • Go: go test ./...
    • Go vet: go vet ./...
    • Go fmt: gofmt -w $(rg --files -g '*.go')

When to use

  • A request is ambiguous or missing required inputs (schemas, env vars, sample payloads, constraints).

Preconditions

  • You have the user’s request in the thread.

Inputs to confirm

  • Required schemas or config samples
  • Runtime constraints (CLI vs API vs UI)
  • Success criteria and scope boundaries

Required artifacts

  • A minimal list of questions
  • A checklist of missing inputs

Quick path

  • Identify missing inputs.
  • Ask the minimum number of questions to proceed.
  • Provide a clear checklist.

Steps

  1. Stop before coding.
  2. Ask 2–6 targeted questions.
  3. Provide a short checklist of missing inputs.
  4. State what you will do next once answered.

Failure modes and responses

  • Too many questions: reduce to only what blocks progress.
  • Vague questions: rewrite as concrete inputs.

Definition of done

  • Missing inputs are explicitly listed and requested.

Example (minimal)

  • Input: “Add a plugin system.”
  • Questions: What transport? What capability schema? Which paths?
  • Gotcha: Don’t implement before protocol is defined.
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. 10d ago First seen · 58 lines · 20 tokens per session scan A 5893d9d17e79

Subscribe to this mod's changes

core-ask-questions-if-underspecified is a skill published in the GitHub repository oodaris/autocodex (16 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 398 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.