MoAI-ADK is a Go-based harness that organizes and verifies Claude Code work across planning, implementation, synchronization, and review stages. Developers use it to structure agentic coding tasks, apply quality gates, and route work across language models, while the catalogue entries extend its workflow with skills, hooks, commands, MCP servers, instructions, and settings.
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 modu-ai/moai-adk --skill moai-ref-jev-question-designgit clone --depth 1 https://github.com/modu-ai/moai-adkWrote 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/modu-ai/moai-adk/moai-ref-jev-question-design)<a href="https://agentmods.dev/skills/modu-ai/moai-adk/moai-ref-jev-question-design"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/moai-ref-jev-question-design/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/modu-ai/moai-adk/moai-ref-jev-question-design"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/moai-ref-jev-question-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00091 | $0.00876 |
| Opus 5.5 | $0.00036 | $0.00350 |
| Sonnet 5.5 | $0.00018 | $0.00175 |
| Haiku 4.5 | $0.00009 | $0.00088 |
Grade A, and why
moai-ref-jev-question-design 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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jev Question Design
The capability answers typed questions over a supplied state and returns a
typed answer with the model's probability. It generates no text and decides
nothing: the answer is a labelled model signal a person reads, never a
completion predicate, a merge approval, a queue mutation, or any other
decision that is hard to undo. A narrow exception is the todo --auto cycle's
own candidate ranking, the auto-scoped ranking exception, which sets
selection order only; it is an in-process consumer behind the default-off
gate. Good questions keep that contract; bad
questions waste the call or manufacture false confidence. Four rules govern
question design.
Rule 1 — Compute the question in code
The question must be computed from the caller's inputs by the caller's code, not improvised as free-form prose at call time. A computed question is reviewable, stable across calls, and testable: the same inputs always compose the same question, and a change in phrasing shows up as a diff. Compose question text with the project's language's string formatting from named inputs — never hand-type a question into a prompt-shaped literal that drifts from the code that acts on its answer.
Rule 2 — Always admit a no-match answer
A choice question whose option set forces a pick manufactures confidence the call cannot have. Every choice question carries an explicit no-match option ("none of these fit", "no listed option") so the answer can say the honest thing. Same discipline for noul questions: ask only when both YES and NO are answers a reader would treat as informative — a question with only one meaningful answer is rhetoric, not a question.
Rule 3 — Keep the state small
Input is charged per token and output is not, so cost tracks state size, not question count. Several questions over one state in one call keep answers mutually consistent and cost nothing extra. Supply the minimum denatured facts the question needs — the axis being judged, the options, the counts that matter — and nothing else. Oversize payloads are refused unsent; a state that must be truncated to fit is a signal to redesign the question, not to trim the payload by hand.
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.
- 11d ago First seen · 83 lines · 91 tokens per session scan A c1fc036cc3b4
moai-ref-jev-question-design is a skill published in the GitHub repository modu-ai/moai-adk (1,234 stars, last pushed 2d ago), licensed Apache-2.0. It adds 91 tokens to every session and 876 once invoked, about $0.0004 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 2026-10-06.
Other skills, from other repositories
hn-summarize
Fetch and summarize Hacker News / hckrnews.com top stories, articles, and their comment threads. Use when asked to summarize HN front-page stories, a specific HN story plus its discussion, or "the top N from hckrnews".
gha
Analyze GitHub Actions failures and identify root causes.
review-claudemd
Review recent conversations to find improvements for CLAUDE.md files.
code-reviewer
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
test-generator
Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.
api-documenter
Auto-generate API documentation from code and comments. Use when API endpoints change, or user mentions API docs. Creates OpenAPI/Swagger specs from code. Triggers on API file changes, documentation requests, endpoint additions.