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 skills/arcblock/agent-skills/blocklet-getting-startednpx skills add ArcBlock/agent-skills --skill blocklet-getting-startedgit clone --depth 1 https://github.com/ArcBlock/agent-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/arcblock/agent-skills/blocklet-getting-started)<a href="https://agentmods.dev/skills/arcblock/agent-skills/blocklet-getting-started"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/blocklet-getting-started.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 | $0.00082 | $0.02696 |
| Opus 5 | $0.00041 | $0.01348 |
| Sonnet 5 | $0.00016 | $0.00539 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade A, and why
blocklet-getting-started 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blocklet Getting Started
An interactive Q&A guide for developers who are new to ArcBlock's Blocklet ecosystem and don't know what questions to ask.
Core Philosophy
"Guide through questions, answer from skills."
This skill maintains a curated list of questions. When user selects a question, AI reads the relevant skill files in plugins/blocklet/skills/ to understand the context and provide accurate answers.
"If users knew what to ask, they wouldn't need this skill."
Users who know their questions can ask AI directly. This skill is for those who need guided discovery.
Workflow
Phase 0: Language Selection
First, use AskUserQuestion to determine the user's preferred language:
Which language do you prefer? / 请选择您的语言 / 言語を選択してください
Options:
A. English
B. 中文 (Chinese)
C. 日本語 (Japanese)
After user selects a language, ALL subsequent communication must be in that language.
Phase 1: Present Questions (Loop)
Use AskUserQuestion to present questions.
Due to UI constraints (max 4 options), present 3 questions + 1 special option:
- 3 questions from different categories (maximize user choice)
- "Start my first environment setup" - Redirect to
/blocklet-dev-setupor/blocklet-server-dev-setup
After answering each question, return to Phase 1 and present the next set of questions (pick different ones).
Question Catalog
Questions are organized by category. When presenting questions, pick 3 from different categories to give variety. Track which questions have been asked to avoid repetition.
Category: Getting Started (GS)
| ID | Question | Answer Source |
|---|---|---|
| GS-1 | What's the difference between developing a Blocklet vs developing Blocklet Server? | Read blocklet-dev-setup/SKILL.md and blocklet-server-dev-setup/SKILL.md, compare their purposes |
| GS-2 | Which skill should I use to start development? | Analyze user's goal, recommend blocklet-dev-setup or blocklet-server-dev-setup |
| GS-3 | What is the complete development workflow from setup to PR? | Read blocklet-dev-setup/SKILL.md Phase 1-7, blocklet-pr/SKILL.md |
| GS-4 | What prerequisites do I need before starting? | Read blocklet-dev-setup/SKILL.md Phase 0 and Phase 3 |
| GS-5 | How do I know if my environment is ready? | Read blocklet-dev-setup/SKILL.md Phase 3 (Prerequisites Check) |
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 · 204 lines · 82 tokens per session scan A b5d7aa3e3280
blocklet-getting-started is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 2,696 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…