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 maksutovic/joycraft --skill joycraft-decidegit 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-decide)<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>- 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 | $0.00044 | $0.04038 |
| Opus 5 | $0.00022 | $0.02019 |
| Sonnet 5 | $0.00009 | $0.00808 |
| Haiku 4.5 | $0.00004 | $0.00404 |
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.
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/parentbrief.md— the brief's frontmatter is where decisions stamp. - No path given: scan
docs/features/*/brief.mdfor briefs with open decisions — a frontmatterdecisions:entry withstatus: open, or an## Open Questionssection with unresolved items. One match → use it and say so. Several → list them and ask which. None → report "no open decisions found" and stop.
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.
- today Changed · +2 lines 9e01a048ec30
- 8d ago First seen · 301 lines · 44 tokens per session scan A 8aa34fd72ce7
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.
Other skills, from other repositories
handoff
Write a portable, secret-scrubbed handoff doc so this work can continue in any AI tool or on any machine. Use when saying "handoff", "running out of tokens", or "continue elsewhere".
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
genie-orca-wish
Turn a brainstorm/design into an APPROVED-able wish whose Dispatch plan is the literal input to Orca tasks and Linear issues. High-reasoning pass: pre-decide everything so fast workers can execute without judgment calls.
bmad-correct-course
Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change".
linear-graphql-skill
Operate Linear workspace issues, projects, and teams through Linear GraphQL API using UXC. Use when tasks require querying or creating issues, managing projects, or interacting with Linear workflow. Supports both Personal API Key and OAuth authentication.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.