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/maksutovic/joycraft/joycraft-interviewnpx skills add maksutovic/joycraft --skill joycraft-interviewgit clone --depth 1 https://github.com/maksutovic/joycraftWrote 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/maksutovic/joycraft/joycraft-interview)<a href="https://agentmods.dev/skills/maksutovic/joycraft/joycraft-interview"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-interview.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.03625 |
| Opus 5 | $0.00015 | $0.01813 |
| Sonnet 5 | $0.00006 | $0.00725 |
| Haiku 4.5 | $0.00003 | $0.00363 |
Grade A, and why
joycraft-interview 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.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview — Idea Exploration
You are helping the user brainstorm and explore what they want to build. This is a lightweight, low-pressure conversation — not a formal spec process. Let them yap.
How to Run the Interview
1. Open the Floor
Start with something like: "What are you thinking about building? Just talk — I'll listen and ask questions as we go."
Let the user talk freely. Do not interrupt their flow. Do not push toward structure yet.
2. Ask Clarifying Questions
How to ask — the question directive. Every question in this skill is asked as structured forced-choice questions asked directly in chat: present the numbered options under the question, then wait for the answer before moving on. Never dump an unanswerable wall of open prose questions. Three rules ride on every question, no exceptions:
-
Every question has ≥2 real options. A one-option question is invalid — reframe it or drop it; a rubber-stamp question captures nothing. Open-ended questions still qualify: offer the 2–4 most likely answers as options and let free text carry anything else.
-
The rationale rides in the free-text answer (Pattern B). When the reason matters, end the question's text with this instruction, verbatim in shape:
Do NOT just pick an option — use the free-text field and type your answer as " because ". If every option here is wrong, reject the framing: type what's right instead.
-
"Defer to " is always a valid answer. A free-text answer of "defer to " (or " knows this") terminates the question as assigned to that person instead of looping. Record it in the artifact's closing "Open Questions — Assigned" section — question, assignee, date, and a context link; the section exists only when at least one question is assigned. Then confirm the deferral in one visible chat line — who, which question, where it was recorded (e.g.
Assigned: Q2 → Sam · recorded in the artifact's Open Questions — Assigned section). Never mutate the file silently on a conversational shortcut. A defer with no name ("someone else knows this") gets exactly one follow-up asking who; without a name the question stays open — never an anonymous assignment. Re-deferring to a different person: the latest assignment wins, and the confirmation line notes the reassignment. If an assigned question is answered later in the session, remove it from the assigned section, record the answer normally, and confirm in one line. Assignment is not backlogging — never auto-write assigned questions todocs/backlog/.
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 Changed 3e647685a5b8
- 6d ago First seen · 318 lines · 29 tokens per session scan A 80833462ce43
joycraft-interview is a skill published in the GitHub repository maksutovic/joycraft (15 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 3,625 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 2026-08-30.
Other skills, from other repositories
code-writing
Universal quality coding process: plan, TDD, reviews. Use whenever code needs to be written — ad-hoc or as part of a task. Use when: "напиши код", "закодь", "реализуй", "write code", "implement" For planning tasks → tech-spec-planning skill. For specs → user-spec-planning skill.
design-retrospective
Analyze design session feedback, extract aesthetic lessons into .design-system/lessons-learned.md, promote recurring patterns to design-principles.md, write taste-profile and cross-project experience, generate context-free next-session prompt. Use when: "дизайн ретроспектива", "design retrospective", "уроки дизайна"…
task-decomposition
Decompose approved tech-spec into atomic task files with parallel creation and validation. Use when: "разбей на задачи", "декомпозиция", "decompose tech-spec", "создай задачи из техспека", "/decompose-tech-spec".
code-reviewing
Code review methodology and quality standards for comprehensive code analysis. Use to understand WHAT and HOW to review code: 11 review dimensions, process, quality standards. Use when: "проверь код", "code review", "ревью кода", "review this code", "check code quality".
design-generate
Generates HTML/CSS pages and static SVG mockups from text descriptions using a project's design system. Selects from 15 layout patterns (5 basic + 10 advanced grids), assembles components, applies tokens, supports iteration via screenshots. After approval, generates diagonal before/after collage. Use when: "сделай…
design-system-init
Creates a project design system through scan and interview. Generates .design-system/tokens.json + standalone HTML components with CSS custom properties. Covers palette (by mood), typography (font pairs), spacing (golden ratio/Fibonacci), radii, shadows, breakpoints. Use when: "создай дизайн-систему", "инициализируй…