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-hardengit 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-harden)<a href="https://agentmods.dev/skills/maksutovic/joycraft/joycraft-harden"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-harden/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-harden"><img src="https://agentmods.dev/badge/skills/maksutovic/joycraft/joycraft-harden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 17 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 | $0.00033 | $0.01279 |
| Opus 5 | $0.00016 | $0.00639 |
| Sonnet 5 | $0.00007 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
joycraft-harden 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 — 97 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.
Harden (Prose Boundaries → Machine Checks)
You are converting eligible ALWAYS/ASK FIRST/NEVER boundary prose into machine-checked
form. Prose is a rule the model merely hopes to follow; a deny pattern or hook enforces it.
Harden is convert-what-exists — it never interviews from scratch (that's joycraft-lockdown).
Step 1: Read the current state
Read the project's boundary file (AGENTS.md, or wherever the ALWAYS/ASK FIRST/NEVER
rules live), .claude/settings.json permissions.deny, and
.claude/hooks/joycraft/deny-patterns.txt. These are the only two enforcement surfaces
you target. Both are installed by Joycraft's safeguard machinery (npx joycraft@latest init) —
you append to the files it produces, you never rewrite the hook script itself, and you
never add a new hook framework.
Note: the enforcement surfaces live on the Claude Code side (.claude/). If this
project has no .claude/ install, harden can still classify rules and stamp provenance,
but there is no machine-check surface to write to — say so and stop after Step 2.
Step 2: Classify each ALWAYS/ASK FIRST/NEVER rule
For every rule, decide eligible or ineligible:
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 · +2 lines 03215b96db25
- 10d ago First seen · 95 lines · 33 tokens per session scan A 3fb9b50cc34f
joycraft-harden is a skill published in the GitHub repository maksutovic/joycraft (15 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,279 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
qamap-pr-qa
Local zero-LLM PR QA workflow. Use when an agent is preparing, updating, finalizing, or reviewing a pull request, asks what the PR should test, or needs commit-backed change intent, affected behavior, QA scenarios, evidence, validation commands, optional automation drafts, and manifest repair guidance.
PR Etiquette
This skill should be used when responding to maintainer review feedback, writing or reviewing PR descriptions, following up on dormant PRs, validating PR quality before submission, or deciding how to communicate with maintainers. Sibling to oss-contribution and contribution-ethics.
NestJS Framework
Node.js/TypeScript backend framework with dependency injection and modular architecture.
using-prisma
Prisma 5+ ORM with schema-first design, type-safe client, migrations, and database integrations (Supabase, PlanetScale, Neon). Use for TypeScript/JavaScript database access.
async-await-patterns
Use when writing JavaScript or TypeScript code with asynchronous operations, fixing promise-related bugs, or converting callback/promise patterns to async/await. Triggers: 'promise chain', 'unhandled rejection', 'race condition in JS', 'callback hell', 'Promise.all', 'sequential vs parallel async', 'missing await'.…
OSS Contribution Best Practices
This skill should be used when the user is working on open source contributions, responding to maintainer feedback, writing PR descriptions, working on issues, following up on dormant PRs, or needs guidance on open source etiquette and best practices.