A decision checkpoint that asks for an explicit choice before an architectural, security, deployment, or other hard-to-reverse change, or when requirements are unclear.

Review options and collect the user's decision before changing architecture, schemas, APIs, deployment plans, or security settings.

It prevents an agent from making a consequential assumption without confirming the intended direction.

ask-user — Skill for Claude Code and Codex by edlsh/pi-ask-user

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 edlsh/pi-ask-user --skill ask-user

Clone the repo

git clone --depth 1 https://github.com/edlsh/pi-ask-user

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/edlsh/pi-ask-user/ask-user/github.svg)](https://agentmods.dev/skills/edlsh/pi-ask-user/ask-user)

Your own site

<a href="https://agentmods.dev/skills/edlsh/pi-ask-user/ask-user"><img src="https://agentmods.dev/badge/skills/edlsh/pi-ask-user/ask-user/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/edlsh/pi-ask-user/ask-user"><img src="https://agentmods.dev/badge/skills/edlsh/pi-ask-user/ask-user.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,699 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 warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 41
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01699
Opus 5.5	$0.00019	$0.00680
Sonnet 5.5	$0.00010	$0.00340
Haiku 4.5	$0.00005	$0.00170

Measured 3d ago against content hash cab1a048232c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ask-user 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 3d 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/ask-user/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask User Decision Gate

Use this skill to force explicit user alignment before consequential decisions.

This skill is about decision control, not general chit-chat.

Non-negotiable rule

Invoke ask_user before proceeding when any of the following is true:

The next step changes architecture, schema, API contracts, deployment strategy, or security posture.
The work is costly to undo (large refactor, migration, destructive edit, production-facing behavior change).
Requirements, constraints, or success criteria are unclear, conflicting, or missing.
Multiple valid options exist and the trade-off is preference-dependent.
You are about to assume something that can materially change implementation.

Do not skip this gate unless the user has already provided a clear, explicit decision for the exact trade-off.

Agent Protocol Handshake (required)

Follow this handshake in order.

1) Detect boundary

Classify the current step as:

high_stakes
ambiguous
both
clear (no gate needed)

If classification is not clear, continue.

2) Gather evidence first

Before asking, gather context from available tools (read, bash, exa, ref, etc.). Do not ask the user to decide blind.

3) Synthesize context

Prepare a short neutral summary (3-7 bullets or short paragraph) covering:

current state
key constraints
trade-offs
recommendation (if any)

4) Ask one focused question

Call ask_user with one decision at a time:

question: concrete decision prompt
context: synthesized summary
options: 2-5 clear choices when possible
allowMultiple: false unless independent selections are genuinely needed
allowFreeform: usually true
displayMode (optional): "overlay" (default) or "inline". Use "inline" when preceding assistant context (summary, trade-offs, recommendation) is essential to the decision and should remain visible — overlays cover the conversation underneath. The user may set a personal default via the PI_ASK_USER_DISPLAY_MODE environment variable or displayMode in ask-user.json; only pass this when you intentionally want to override it for one call.
contextExpanded (optional): true opens oversized context fully expanded instead of collapsed behind a one-line summary. The user may set a personal default via PI_ASK_USER_CONTEXT_EXPANDED or contextExpanded in ask-user.json; only pass this when the context is the evidence the user needs to weigh the options.

Read the full file on GitHub · 190 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/ask-user-skill-extension-spec.md 4.1 KB

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.

3d ago Changed cab1a048232c
20d ago Changed · +26 lines 5811ecd9d537
1mo ago Changed f1aaf14ce913
1mo ago Changed · +1 lines 6ed9c3ef88a7
1mo ago First seen · 163 lines · 48 tokens per session scan A 4e7615a29066

Subscribe to this mod's changes

ask-user is a skill published in the GitHub repository edlsh/pi-ask-user (174 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,699 once invoked, about $0.0002 per session on Opus 5.5. 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.

Planning TypeScript ai-agents ai-assistant cli internal-tool status-active

async-await-patterns

Use when writing JavaScript or TypeScript code with asynchronous operations, fixing promise-related bugs, or converting callback/promise patterns to async/await. Triggers: 'promise chain', 'unhandled rejection', 'race condition in JS', 'callback hell', 'Promise.all', 'sequential vs parallel async', 'missing await'.…

axiomantic/spellbook · 81 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

adding-a-command

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing…

caliber-ai-org/ai-setup · 76 tokens

scaffold-project

Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…

Marve10s/Better-Fullstack · 80 tokens

add-to-project

Add capabilities, addons, deployment targets, generated CI, services, or stack updates to an existing Better Fullstack project. Use when the current repo has bts.jsonc or the user asks to extend a generated project. Prefer bfsplanstackupdate and bfsapplystackupdate; use legacy addon tools only for addon/deploy-only…

Marve10s/Better-Fullstack · 71 tokens

agent-dependencies

Perform one conservative dependency or toolchain upgrade in the Elements monorepo and open a validated pull request. Use for nightly or unattended dependency maintenance, outdated package checks, first-party actions/ GitHub Actions updates, and pinned mise tool updates. Use the github-dependabot skill instead when the…

NVIDIA/elements · 73 tokens