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/nlinhvu/learn-java-frameworks-marketplace/api-buildernpx skills add nlinhvu/learn-java-frameworks-marketplace --skill api-buildergit clone --depth 1 https://github.com/nlinhvu/learn-java-frameworks-marketplaceWhat 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 | $0.00102 | $0.03704 |
| Opus 5 | $0.00051 | $0.01852 |
| Sonnet 5 | $0.00020 | $0.00741 |
| Haiku 4.5 | $0.00010 | $0.00370 |
Grade A, and why
api-builder 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Builder — API-First Implementation
Philosophy: API Contract First, Then Implement Inward
Each feature is a vertical slice — a single API capability traced from the source project's public surface down through every internal layer needed to make it work. The source project can be in any language (Python, Go, Rust, Node.js, C#, Ruby, Java, etc.), but the output is always a simplified Java reimplementation. The implementation follows the same direction a contributor would: "I see the API, I want to understand how it works, so I trace the code from the public method inward."
This produces two artifacts, one truth:
- Working Java code in
src/— compiles, tests pass, is the source of truth - Rich tutorial chapter in
api-docs/— reads back actual source files, never diverges, enriched with ★ Insight blocks and Mermaid diagrams at every design decision
Every simplification choice, layer boundary, technology mapping decision, and API design decision is a teaching moment. The learner doesn't just see WHAT was built — they understand WHY each choice was made and what alternatives were considered.
MANDATORY: Use Extended Thinking
Use extended thinking before implementing. The quality of the vertical slice depends on deep upfront reasoning about both the source project and the simplified Java version. Before writing any code:
- Study the source project's API contract and its full call chain from surface to internals (in any language)
- Design the simplified Java public API class/interface — method signatures, parameter types, return types
- Plan the depth layers — which layers this feature needs and what to simplify at each
- Map source language concepts to Java equivalents (e.g., Python decorators to annotations, Go channels to queues)
- Determine what to reuse and extend from prior features' internals
- Design the client-perspective tests that will define the API's behavioral contract
Skipping extended thinking leads to vertical slices with incorrect API contracts, missing depth layers, or implementations that break prior features' tests.
What ships with it
2 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.
- 2d ago First seen · 359 lines · 102 tokens per session scan A 4d60d9454b06
api-builder is a skill published in the GitHub repository nlinhvu/learn-java-frameworks-marketplace (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 102 tokens to every session and 3,704 once invoked, about $0.0005 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
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…