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-new-featuregit 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-new-feature)<a href="https://agentmods.dev/skills/maksutovic/joycraft/joycraft-new-feature"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-new-feature/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/maksutovic/joycraft/joycraft-new-feature"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-new-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 41 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00025 | $0.05950 |
| Opus 5.5 | $0.00010 | $0.02380 |
| Sonnet 5.5 | $0.00005 | $0.01190 |
| Haiku 4.5 | $0.00003 | $0.00595 |
Grade A, and why
joycraft-new-feature 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 1mo 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 — 505 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.
New Feature Workflow
You are starting a new feature. Follow this process in order. Do not skip steps.
Phase 0: Check for Existing Drafts and In-Flight Features
Before starting the interview, scan docs/features/ for existing artifacts the user may want to continue from.
Skip this phase if: the user provided a brief path or an intent path (docs/intent/<name>.md) as an argument (they already know what to work from).
Given an intent path: read the file (its shape is docs/templates/INTENT_TEMPLATE.md) and pre-fill Phase 1 from it — Problem frames the problem in the brief's Vision, Proposed outcome feeds Vision and Success Criteria, Affected users and systems feeds User Stories, Constraints feeds Hard Constraints, and Open questions become your opening interview questions instead of a blank floor. Ask about any missing section through the question directive. If the intent path does not exist, say so in one line and fall back to the no-argument flow. If its Status: already says it was consumed, tell the human by which skill and proceed only on their go-ahead. Normalize the path to project-relative before writing it into the brief's intent: key (Phase 2). After writing the brief, overwrite the intent's Status: line in place with Status: consumed by joycraft-new-feature → docs/features/<slug>/brief.md (YYYY-MM-DD). The intent file stays in docs/intent/ — never move, delete, or archive it.
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.
- 1mo ago Changed · +5 lines eab5f59c8ebb
- 2mo ago Changed · +2 lines baed27584bd4
- 2mo ago First seen · 498 lines · 25 tokens per session scan A b9f65b7d2658
joycraft-new-feature is a skill published in the GitHub repository maksutovic/joycraft (15 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 5,950 once invoked, about $0.0001 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 2026-08-30.
joycraft-new-feature compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| joycraft-new-featuremaksutovic/joycraft | Skill | 15 | 3d ago | MIT | A | 25 | Claude Code, Codex |
| NestJS FrameworkFortiumPartners/ensemble | Skill | 12 | 2d ago | MIT | A | 17 | Claude Code, Codex |
| using-prismaFortiumPartners/ensemble | Skill | 12 | 2d ago | MIT | A | 43 | Claude Code |
| dd-code-generationDataDog/pup | Skill | 1.0k | today | Apache-2.0 | A | 16 | Claude Code |
| adding-a-commandcaliber-ai-org/ai-setup | Skill | 1.3k | 1mo ago | MIT | A | 76 | Claude Code, Codex |
| scaffold-projectMarve10s/Better-Fullstack | Skill | 818 | today | MIT | A | 80 | Claude Code |
| add-to-projectMarve10s/Better-Fullstack | Skill | 818 | today | MIT | A | 71 | Claude Code |