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-implement-level5git 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-implement-level5)<a href="https://agentmods.dev/skills/maksutovic/joycraft/joycraft-implement-level5"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-implement-level5/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-implement-level5"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-implement-level5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium MCP Rug Pull · line 14 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 67 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00039 | $0.01918 |
| Opus 5.5 | $0.00016 | $0.00767 |
| Sonnet 5.5 | $0.00008 | $0.00384 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
joycraft-implement-level5 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 — 167 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.
Implement Level 5 — Autonomous Development Loop
You are guiding the user through setting up Level 5: the autonomous feedback loop where specs go in, validated software comes out. This is a one-time setup that installs workflows, creates a scenarios repo, and configures the autofix loop.
Before You Begin
Check prerequisites:
- Project must be initialized. Look for
docs/.joycraft/manifest.jsonordocs/.joycraft/local/manifest.json. Older installs may still have state atdocs/.joycraft/state.json,.claude/.joycraft/state.json, or.joycraft-versionat the repo root. If none exist, tell the user to runnpx joycraft@latest initfirst. - Project should be at Level 4. Check
docs$joycraft-assessment.mdif it exists. If the project hasn't been assessed yet, suggest running$joycraft-tunefirst. But don't block — the user may know they're ready. - Git repo with GitHub remote. This setup requires GitHub Actions. Check for
.git/and a GitHub remote.
If prerequisites aren't met, explain what's needed and stop.
Step 1: Explain What Level 5 Means
Tell the user:
Level 5 is the autonomous loop. When you push specs, three things happen automatically:
- Scenario evolution — A separate AI agent reads your specs and writes holdout tests in a private scenarios repo. These tests are invisible to your coding agent.
- Autofix — When CI fails on a PR, Claude Code automatically attempts a fix (up to 3 times).
- Holdout validation — When CI passes, your scenarios repo runs behavioral tests against the PR. Results post as PR comments.
The key insight: your coding agent never sees the scenario tests. This prevents it from gaming the test suite — like a validation set in machine learning.
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 · +2 lines 1409cc994f0b
- 1mo ago First seen · 165 lines · 39 tokens per session scan A bd719467d595
joycraft-implement-level5 is a skill published in the GitHub repository maksutovic/joycraft (15 stars, last pushed 29d ago), licensed MIT. It adds 39 tokens to every session and 1,918 once invoked, about $0.0002 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.
Other skills, from other repositories
agent-upkeep
Perform one small, scoped maintenance improvement to the Elements monorepo and open a single reviewable pull request. Use this skill for scheduled or unattended upkeep runs that improve unit test coverage for one file, fix one behavioral bug in one module, or move one off ESLint rule toward enforcement to reduce…
authoring-benchmarks
Design, implement, run, debug, and interpret browser performance benchmarks for Elements components and utilities. Use whenever the user asks to benchmark or performance-test runtime code, create or update a .test.bench.ts file, compare benchmark results, investigate a browser performance regression, understand Vitest…
agent-starters
Verify every starter supported by the stable production NVIDIA Elements CLI from a fresh consumer environment, investigate failures, and prepare at most one focused repair pull request. Use for nightly or scheduled production starter verification and starter availability failures.
audit-ci
Run and analyze Elements cold CI performance profiles and propose evidence-backed build, test, lint, and dependency-graph improvements. Use whenever asked to profile or benchmark pnpm run ci, rerun ci:profile, create a CI performance audit, compare CI timings, find bottlenecks or the completion path, investigate a CI…
authoring-projects
Author a new standalone NVIDIA Elements workspace project containing a Lit component, including package files, the five test types, Wireit tasks, workspace and CI registration, metadata generation, documentation-site integration, dependency-lint configuration, and generated lock/notice files. Use when creating or…
audit-accessibility
Unified accessibility auditing workflow across static analysis, runtime testing, ARIA patterns, keyboard navigation, and color contrast. Use this skill whenever the user mentions accessibility, a11y, WCAG, ARIA roles, axe tests, screen readers, focus management, keyboard navigation, color contrast, or wants to audit…