JetBrains/thinkrail is a desktop and mobile client that embeds the pi coding agent inside an interface for editing code and managing development workspaces. Developers use it to work on Git repositories through separate worktrees, a Monaco editor, terminals, Git views, specifications, and concurrent agent sessions. The catalogue entries are skills and instructions for its agent-based development workflow.
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 skills add JetBrains/thinkrail --skill asking-user-questionsgit clone --depth 1 https://github.com/JetBrains/thinkrailWrote 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/jetbrains/thinkrail/asking-user-questions)<a href="https://agentmods.dev/skills/jetbrains/thinkrail/asking-user-questions"><img src="https://agentmods.dev/badge/skills/jetbrains/thinkrail/asking-user-questions/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.
<a href="https://agentmods.dev/skills/jetbrains/thinkrail/asking-user-questions"><img src="https://agentmods.dev/badge/skills/jetbrains/thinkrail/asking-user-questions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00948 |
| Opus 5 | $0.00022 | $0.00474 |
| Sonnet 5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
asking-user-questions 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asking User Questions
The workflow family's shared norms for ask_user_question: how to compose rounds, shape options, and
degrade when answers don't come. Process skills name this concept at the steps that ask; when to ask
— and where the answers get recorded — stays with the referencing skill.
Rounds, not chat turns
- One call = one round: up to 4 questions, 2–4 options each. Group everything the current step needs into a single round — never chain a second call straight after for a trivial follow-up.
- The call ends your turn. The questionnaire is shown and your run stops; the answers arrive as the next user message (a structured "User has answered your questions:" message). Don't keep working on the blocked step after calling, and don't assume an answer until it arrives — whether that is seconds later or days later.
- If the user replies with a free-form message instead of answering the card, that reply supersedes the round — treat it as their answer, and re-ask only what is still genuinely undecided.
- Resolve the round, act on what you learned, and open a new round only when the answers raised a genuinely new question.
Options
- Recommended option first, label suffixed "(Recommended)", plus a one-line
recommendedReasonsaying why you recommend it over the alternatives (shown inline under the option as aWhy:line). - Every option: a concise label (1–5 words, ≤ 60 chars) + a description carrying the trade-off or consequence of choosing it. Tailor options to the work at hand — never generic placeholders.
- Options must be decidable by the asked user: frame them as observable behavior or outcomes ("collapsing a project stays collapsed after a rename"), never as implementation mechanics ("semantic guard", "activation ref"). If candidate options differ only internally — identical observable behavior — don't ask: decide yourself and record the reasoning in the workflow's artifact.
- Never author your own "Other", free-text, or escape options — the tool adds a free-text row to
every question and an always-available Skip, and reserved labels are rejected. This holds under
multiSelecttoo: the free-text row stays and is additive — a typed answer arrives alongside the checked options, it does not replace them. multiSelect: truewhen several answers are valid at once (feature checklists); single-select when confirming something or choosing one path.options[].preview(markdown) when a concrete artifact — code, a config, a mockup — is clearer shown than described. Single-select only.headeris a short chip, ≤ 16 characters.
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.
- 9d ago First seen · 67 lines · 43 tokens per session scan A 8725dace0254
asking-user-questions is a skill published in the GitHub repository JetBrains/thinkrail (427 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 948 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 2026-08-30.
Other skills, from other repositories
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
hunt-xxe
Hunting skill for xxe vulnerabilities. Built from 4 public bug bounty reports. Use when hunting xxe on any target.
vigilante-create-issue
Help a human author write an implementation-ready GitHub issue that Vigilante can execute reliably.
detecting-fileless-malware-techniques
Detects and analyzes fileless malware that operates entirely in memory using PowerShell, WMI, .NET reflection, registry-resident payloads, and living-off-the-land binaries (LOLBins) without writing traditional executable files to disk. Activates for requests involving fileless threat detection, in-memory malware…
detecting-process-injection-techniques
Detects and analyzes process injection techniques used by malware including classic DLL injection, process hollowing, APC injection, thread hijacking, and reflective loading. Uses memory forensics, API monitoring, and behavioral analysis to identify injection artifacts. Activates for requests involving process…