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.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/elicit/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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.
[](https://agentmods.dev/skills/smart-ai-memory/attune-ai/elicit)<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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.
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.
- today Changed · +202 lines · -12 tokens per session b28ea91391a7
- yesterday Changed · +35 lines 32b56ef27561
- 8d ago First seen · 458 lines · 48 tokens per session scan A 0c3a249e4619
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.
Other skills, from other repositories
eco-max
Maximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any language.
eco
Token-frugal mode - minimize token consumption (concise replies, lean tool use, cheap delegation) at full task quality. Use when the user mentions tokens, cost, budget, quota, or economical operation, in any language. Invoke once; applies for the rest of the session. "/eco setup" configures permanent savings.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
template-engine
Load, validate, and populate templates consistently across frameworks.
checkpoint
Create, list, or recover mid-workflow checkpoints so interrupted work resumes from a known-good position.