joycraft-decide

joycraft-decide is a skill for Claude Code, Codex from maksutovic/joycraft. It costs 44 tokens per session (4,038 once invoked), scanned A, original, MIT.

A skill for resolving unanswered design questions through a structured decision record. Each question ends as clarified, postponed, discarded, or assigned to someone.

In plain words
What is it for?
It is for reviewing a design brief, presenting the surrounding context, and recording decisions or follow-up ownership.
Why use it?
It makes uncertain design choices explicit so development does not proceed while important questions remain open.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; $skill-name invocation.

Good fit It is for reviewing a design brief, presenting the surrounding context, and recording decisions or follow-up ownership.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/maksutovic/joycraft/joycraft-decide
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 maksutovic/joycraft --skill joycraft-decide
Clone the repo
git clone --depth 1 https://github.com/maksutovic/joycraft

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.

agentmods badge for joycraft-decide

README.md
[![agentmods](https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-decide.svg)](https://agentmods.dev/skills/maksutovic/joycraft/joycraft-decide)
Your own site
<a href="https://agentmods.dev/skills/maksutovic/joycraft/joycraft-decide"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-decide.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,038 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 pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.04038
Opus 5 $0.00022 $0.02019
Sonnet 5 $0.00009 $0.00808
Haiku 4.5 $0.00004 $0.00404

Measured today against content hash 9e01a048ec30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

joycraft-decide 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 today.

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.

.agents/skills/joycraft-decide/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

At skill entry, run node docs/.joycraft/check.mjs check --json --session <session-id> once, reusing JOYCRAFT_SESSION_ID if supplied or one ID chosen for this conversation. If the checker is missing or fails, continue the requested skill quietly without retrying setup. Offer updates only for display: true; current, postponed, off, and unknown stay quiet. If automaticUpdate is present, finish this skill, then run its exact command once from the project root: the candidate must verify every safety gate before applying. Other updates require approval. After an offer or automatic attempt, record it with node docs/.joycraft/check.mjs acknowledge <available-version> --session <session-id>. Apply updates only at this workflow boundary; after success, reinvoke the skill or restart the session to load changed instructions.

Decide (Deposition Checkpoint)

You are running the decision checkpoint at the design bookend. The human does not read-and-hope; they get a decision dossier (context brought TO the decision) and answer forced-choice questions with a one-sentence typed rationale each. Every open question leaves this skill in exactly one terminal state: clarified, backlogged, discarded, or assigned (deferred to a named person). The decompose gate stays closed while any decision is still open.

Two hard rules frame everything below:

  • The dossier is display-only. All capture happens in the native question flow (structured forced-choice questions asked directly in chat) — never via interactive HTML, pick-strings, or paste-backs.
  • Never certify your own framing as complete (RF-KILL-3). The questions are YOUR framing of what's open; the assumptions manifest exists to expose what you did NOT ask. Label every unchecked load-bearing claim UNVERIFIED (RF-5) — when in doubt, Unverified.

Step 1: Locate the brief

  • Path given ($joycraft-decide <brief-or-design path>): use it. If it's a design doc, also read the sibling/parent brief.md — the brief's frontmatter is where decisions stamp.
  • No path given: scan docs/features/*/brief.md for briefs with open decisions — a frontmatter decisions: entry with status: open, or an ## Open Questions section with unresolved items. One match → use it and say so. Several → list them and ask which. None → report "no open decisions found" and stop.

Read the full file on GitHub · 303 lines

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.

  1. today Changed · +2 lines 9e01a048ec30
  2. 8d ago First seen · 301 lines · 44 tokens per session scan A 8aa34fd72ce7

Subscribe to this mod's changes

joycraft-decide is a skill published in the GitHub repository maksutovic/joycraft (15 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 4,038 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.