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.
npx agentmods add skills/plmbr/nui/ask-usernpx skills add plmbr/nui --skill ask-usergit clone --depth 1 https://github.com/plmbr/nuiWhat 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 | $0.00017 | $0.00519 |
| Opus 5 | $0.00009 | $0.00260 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
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 2d 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.
What it actually says
Ask User (nui HITL)
When you need any input, clarification, preference, or approval from the human, use the nui-hitl MCP tool ask_user. Do not ask those questions only in assistant text — the human answers through the nui UI prompt card.
When to use ask_user
- The user asks you to ask clarifying questions before continuing
- You need a choice between options (cuisine, scope, constraints, etc.)
- You would otherwise write "Which do you prefer?" or list questions in the chat
- You need structured answers before taking a consequential action
How to call it
Use the MCP tool ask_user on server nui-hitl with a questions array. Each question object can include:
question— the prompt text (required)header— short label shown in the UI (optional)options— array of{ "label": "...", "description": "..." }for multiple choice (optional)
Example:
{
"title": "Recipe preferences",
"questions": [
{
"header": "Region",
"question": "Which South American country or region should the recipe focus on?",
"options": [
{ "label": "Peru", "description": "Andean / coastal Peruvian" },
{ "label": "Argentina", "description": "Grilled meats, empanadas" },
{ "label": "Brazil", "description": "Feijoada, moqueca, etc." }
]
},
{
"header": "Diet",
"question": "Any dietary restrictions?",
"options": [
{ "label": "None" },
{ "label": "Vegetarian" },
{ "label": "Gluten-free" }
]
}
]
}
Wait for the tool result (answers from the human), then continue with the task using those answers.
Tool approval
For yes/no gates before risky actions, use request_approval on nui-hitl instead of ask_user.
Do not
- List clarification questions in plain assistant text when
ask_useris available - Proceed with assumptions when the user explicitly asked you to clarify first
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.
- 2d ago First seen · 63 lines · 17 tokens per session scan A 83cb50bdbbeb
ask-user is a skill published in the GitHub repository plmbr/nui (5 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 519 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 2026-08-31.
Other skills, from other repositories
apple-tools
Reach Apple PIM data (Calendar, Contacts, Reminders, Messages, Location, Maps, Weather) from a pi session via iMCP + pi-mcp-adapter on macOS. Use when the user asks to read/search their Apple Calendar, Contacts, Reminders, iMessages, current Location, Maps, or Weather. Does NOT cover Apple Mail — iMCP exposes no Mail…
list-learned-actions
Explicit Codex workflow: List persisted reusable actions, UI skeletons, and legacy feedback memories before composing device primitives.
agentlas-operations
Agentlas 시스템 운용 절차 — hep-network 편성, hep-graph 자동화, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약. One(개인 에이전트)이 Agentlas를 조작할 때 이 절차를 따른다.
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
release-cut
Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…