attune-ai: Skill for Claude Code

.agents/skills/elicit/SKILL.md

elicit is a skill for Claude Code, Codex from Smart-AI-Memory/attune-ai. It costs 36 tokens per session (8,184 once invoked), scanned A, original, Apache-2.0.

A form-based discovery tool that collects several independent decisions together, such as a project's goal, scope, and focus. It validates both the form and the answers.

In plain words
What is it for?
Use it to clarify the scope of a task, gather project requirements, or make several related decisions in one form. It supports selecting multiple options where appropriate.
Why use it?
It avoids a long sequence of separate questions when the needed choices can be made at once. This makes early requirements gathering more organized.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; mentions Claude Code; installed under .agents/ (shared by several agents).

This is Smart-AI-Memory/attune-ai's own configuration. It tells Claude Code and Codex how to work on attune-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything attune-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/elicit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

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 elicit

README.md
[![agentmods](https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/elicit.svg)](https://agentmods.dev/skills/smart-ai-memory/attune-ai/elicit)
Your own site
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/elicit"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/elicit.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,184 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00036 $0.08184
Opus 5 $0.00018 $0.04092
Sonnet 5 $0.00007 $0.01637
Haiku 4.5 $0.00004 $0.00818

Measured today against content hash b28ea91391a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

elicit 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.

.agents/skills/elicit/SKILL.md · 695 lines

How it starts

The opening of the file, as written. The whole thing — 695 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Elicit — form-driven Socratic discovery

IMPORTANT: Start your response by telling the user:

Elicit — Gathering the independent dimensions of your decision as one form (multi-select where it fits), instead of asking one button at a time.

This skill turns a declarative form (data, not code) into a validated interaction. Apply the host guidance below before building a form; the user need not name a form or tool. The compatibility path uses:

  • elicitation_render_form — validate the form, get batched payloads.
  • elicitation_collect_response — validate the answers (R4).

When to render a multi-field form (the batching rule)

Batch 2–4 fields into one form-turn only when ALL hold:

  • the fields are independent dimensions of one decision the user makes together (e.g. spec kickoff: goal + scope + focus), AND
  • answers don't branch on each other (if a field's relevance depends on another's answer, stay sequential), AND
  • each field is genuinely ambiguous — a dimension the user already specified is omitted, not asked.

Stay single-question when only one dimension is unknown, a later question depends on an earlier answer, or batching would feel like a bureaucratic intake for a simple ask. The form never adds fields the ordinary Socratic-ambiguity judgement wouldn't already ask.

Host defaults — apply before steps 0–4

Do not add durable storage of answer contents as a side effect of asking. Keep working answers in the conversation; explicitly requested artifacts remain subject to the user's existing scope and authorization.

Codex: built-in questions first

For an ordinary planning or scoping request, apply the batching rule and honor explicit conversation preferences. When questions are useful, use Codex's available built-in question tool directly; do not require the user to ask for a form. Discover the tools exposed in this session. At the time of writing, Default mode exposes request_user_input_async; use request_user_input only where the current host/mode permits it. Follow the actual tool schema and limits, including its question-count limit; never invent unsupported controls. Do not add an "Other" option when the tool schema already supplies free-text entry. Put a recommendation first only when justified. Use free text for information that has no honest predefined choices.

Read the full file on GitHub · 695 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. today Changed · +202 lines · -12 tokens per session b28ea91391a7
  2. yesterday Changed · +35 lines 32b56ef27561
  3. 8d ago First seen · 458 lines · 48 tokens per session scan A 0c3a249e4619

Subscribe to this mod's changes

elicit is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 8,184 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.