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 agentmods add instructions/maksutovic/joycraft/agents-mdgit 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/instructions/maksutovic/joycraft/agents-md)<a href="https://agentmods.dev/instructions/maksutovic/joycraft/agents-md"><img src="https://agentmods.dev/badge/instructions/maksutovic/joycraft/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02067 | $0.02067 |
| Opus 5 | $0.01033 | $0.01033 |
| Sonnet 5 | $0.00413 | $0.00413 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
joycraft AGENTS.md 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 3d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Joycraft
What: A CLI + Claude Code plugin that scaffolds and upgrades AI development harnesses. npx joycraft init installs skills, templates, boundaries, and documentation structure into any project, taking it from Level 1 to Level 4 on Dan Shapiro's 5 Levels of Vibe Coding.
Component: npm package (CLI) + Claude Code skills | Updated: 2026-07-21
Behavioral Boundaries
ALWAYS
- Run
pnpm test && pnpm typecheckbefore committing (pnpm testalready runs once and exits —--runis not a valid pnpm flag here and fails) - Run
pnpm sync-skillsafter editing anything undersrc/skills/orsrc/local-skills/, and commit the regenerated + installed copies in the same commit — a stale installed tree is what shipped twelve wrong copilot skills in 0.7.3 - Commit style:
verb: concise message - Reference atomic specs when implementing features — each spec is in
docs/features/<slug>/specs/ - Test against multiple stack types (Node.js, Python, Rust, Go at minimum)
- Push to feature branches after each commit
- Open a PR when all specs in a feature are complete
- Use descriptive branch names: feature/spec-name
ASK FIRST
- Adding dependencies — this is a CLI tool, keep it minimal
- Changing template content — templates are the core product, changes affect all users
- Changing skill content — skills are the user-facing interface
- Modifying the CLAUDE.md merge/improve logic — this touches user files
- Publishing to npm
- Merging PRs to main/master
- Any destructive git operation (force-push, reset --hard, branch deletion)
NEVER
- Overwrite user files without explicit confirmation or
--forceflag - Add runtime dependencies that aren't strictly necessary
- Reference absolute paths — all templates and skills must use project-relative paths
- Include methodology research, project assessments, or personal notes in the tool
- Push directly to main/master (always use feature branches + PR)
- Amend commits that have been pushed to remote
- Access, read, or reference the scenarios repo (
joycraft-scenarios) - Mention scenario test names or contents
- Modify the scenarios dispatch workflow to leak test information
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.
- 3d ago First seen · 193 lines · 2,067 tokens per session scan A 0fffab637b62
joycraft AGENTS.md is an instructions file published in the GitHub repository maksutovic/joycraft (15 stars, last pushed 22d ago), licensed MIT. It adds 2,067 tokens to every session, about $0.0103 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 instructions, from other repositories
ai-dev-methodology-codex AGENTS.md
AGENTS.md instructions for stepanenkoviktor0110-boop/ai-dev-methodology-codex, covering global preferences, ⛔ rule #0: auto-update before any pipeline step, instruction tone: strict by default, skill execution: no scripts and recovery after interruption.
FrameCode-VibeWork AGENTS.md
Instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.
ai-workflow-kit AGENTS.md
Instructions for silver2dream/ai-workflow-kit, covering agents.md (worker agent guide), role: senior engineer (worker), must-read (before any work), non-negotiable hard rules and 0. use existing architecture & do not reinvent.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.
get-design-done CLAUDE.md
Instructions for 0martinez/get-design-done, covering get design done (gdd), what this is, architecture, key commands and key files.
Codex-OS AGENTS.md
AGENTS.md instructions for forsonny/Codex-OS, covering codex-os — project guidance, custom commands, command reference, product context and standards.