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 Z-Bra0/Scratch-Skills --skill scratch-blocksgit clone --depth 1 https://github.com/Z-Bra0/Scratch-SkillsWrote 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/z-bra0/scratch-skills/scratch-blocks)<a href="https://agentmods.dev/skills/z-bra0/scratch-skills/scratch-blocks"><img src="https://agentmods.dev/badge/skills/z-bra0/scratch-skills/scratch-blocks/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/z-bra0/scratch-skills/scratch-blocks"><img src="https://agentmods.dev/badge/skills/z-bra0/scratch-skills/scratch-blocks.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.01333 |
| Opus 5.5 | $0.00015 | $0.00533 |
| Sonnet 5.5 | $0.00008 | $0.00267 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
scratch-blocks 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scratch Code Assistant
Output Contract
scratch-jsonis internal-only. Never paste it into the final user reply.- If you show Scratch code or block structure to the user, you must run
scripts/render_ascii.pyand use its exact output. - Use
scratch-jsononly for tool input and internal reasoning. - If you mention Scratch code, show rendered blocks instead of describing the code only in prose whenever practical.
- Use rendered block output in fenced code blocks.
- Do not add a follow-up like "Want me to render an example?".
- Do not rewrite, add, split, or restyle the rendered Scratch blocks.
- Do not hand-draw, imitate, or approximate Scratch block ASCII from memory.
Goal
Help with Scratch code questions by representing Scratch projects into
scratch-json when needed, reasoning over that internal representation, and
showing Scratch code to the user through scripts/render_ascii.py instead of
raw JSON. For conceptual questions, prefer a visual rendered example over prose-only explanation.
Repo Usage
- Read files under
references/when you need skill guidance or file-handling instructions. - Files under
data/are runtime assets used byscripts/, not AI-facing reference docs. - Do not read files under
data/as reference material.
Internal scratch-json Reference
scratch-json is an internal working format for the AI. Do not return it to the user.
scratch-json is a flat JSON array of objects. Each object repeats its owning target, which can represent a Sprite or the Stage.
This is different from raw Scratch project.json / sprite.json. If you have a raw Scratch file, run scripts/extract.py first.
Each object includes:
| Field | Type | Description |
|---|---|---|
type |
string | script, variable, or list |
target |
string | Owning sprite or stage name |
variable Structure
| Field | Type | Description |
|---|---|---|
name |
string | Variable name |
value |
any | Current value |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 134 lines · 38 tokens per session scan A ddfb1cf25635
scratch-blocks is a skill published in the GitHub repository Z-Bra0/Scratch-Skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 1,333 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.