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 WaniWani-AI/sdk --skill migrate-waniwani-sdk-0.16-to-0.17git clone --depth 1 https://github.com/WaniWani-AI/sdkWrote 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/waniwani-ai/sdk/migrate-waniwani-sdk-0.16-to-0.17)<a href="https://agentmods.dev/skills/waniwani-ai/sdk/migrate-waniwani-sdk-0.16-to-0.17"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/migrate-waniwani-sdk-0.16-to-0.17/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/waniwani-ai/sdk/migrate-waniwani-sdk-0.16-to-0.17"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/migrate-waniwani-sdk-0.16-to-0.17.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00177 | $0.01691 |
| Opus 5 | $0.00088 | $0.00846 |
| Sonnet 5 | $0.00035 | $0.00338 |
| Haiku 4.5 | $0.00018 | $0.00169 |
Grade A, and why
migrate-waniwani-sdk-0.16-to-0.17 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 12d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate @waniwani/sdk 0.16 → 0.17
A self-contained migration for the single hop from 0.16.x to 0.17.0. Apply it when a project on 0.16 is moving to 0.17. It covers only that jump; for other version boundaries use the matching migrate-waniwani-sdk-<from>-to-<to> skill, or the general procedure in the SDK's changelog.
Precondition: the project is on @waniwani/[email protected]. If it is on an older version, migrate up to 0.16 first (that jump ships its own migration); if it is already on 0.17+, there is nothing to do here.
What 0.17 changes
useWaniwani() from @waniwani/sdk/mcp/react is now purely host-agnostic: it resolves its config (endpoint, source, widget token, session id) from explicit options or from a toolResponseMetadata object you pass, and nothing else. It no longer reads a WidgetProvider context and no longer opens its own connection to the widget host to discover the config.
Why: on an MCP-Apps host the tool response _meta (which carries the Waniwani config) is delivered once, to whichever host bridge is connected and listening at that moment. In a skybridge widget that bridge is skybridge. The hook opening a second connection raced the first and missed the one-shot on Claude, so the old auto-discovery was unreliable. The fix makes the core hook take the metadata as data, and adds a skybridge adapter entry that supplies it.
This break is invisible to tsc. A bare useWaniwani() still typechecks — it just returns a no-op widget at runtime (no sessionId, track.* does nothing). So you cannot find the call sites by chasing type errors the way earlier SDK migrations worked. Find them by auditing imports of useWaniwani (step 2).
Procedure
- Bump the dependency.
bun add @waniwani/sdk@^0.17.0 - Find every
useWaniwanicall site. Grep for imports ofuseWaniwanifrom@waniwani/sdk/mcp/react:
For each, apply the case below that matches. A call that already passesrg -l "from \"@waniwani/sdk/mcp/react\"" | xargs rg -l "useWaniwani"endpoint(Case C) needs no change. - Verify — this is the completion check.
bun run typecheck bun testtypecheckwill pass whether or not you migrated (the break is a runtime no-op, not a type error), so it is a guard against regressions, not the signal that the migration is complete. The signal is: every bareuseWaniwani()call site has been moved to Case A, B, or C. - Report which case each call site took, and any host you could not classify (flag for a human).
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.
- 12d ago First seen · 95 lines · 177 tokens per session scan A 200be75a1b82
migrate-waniwani-sdk-0.16-to-0.17 is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed yesterday), licensed MIT. It adds 177 tokens to every session and 1,691 once invoked, about $0.0009 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
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
fluent-development
This skill should be used when the user asks to "build a fluent app", "create a servicenow app in typescript", or mentions "servicenow sdk", "now-sdk", "fluent", "scoped app as code", or "pro-code development" — or when the working directory contains a now.config.json or .now.ts files.
implementing-jsc-classes-rust
Creates JavaScript classes using Bun's Rust bindings generator (.classes.ts). Use when implementing new JS APIs in Rust with JSC integration, prototypes, or constructors.
sdk
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (@cursor/sdk). Use when the user mentions integrating, installing, or writing code against the Cursor SDK; says Agent.create, Agent.prompt, Agent.resume, agent.send, run.stream, CursorAgentError, or @cursor/sdk; asks…
typescript-lsp
Search TypeScript SYMBOLS (functions, types, classes) - NOT text. Use Glob to find files, Grep for text search, LSP for symbol search. Provides type-aware results that understand imports, exports, and relationships.
kernelcad-authoring
Author or modify kernelCAD models in TypeScript. Scripts live in .kcad.ts files; the kernelCAD CLI (kernelcad evaluate and kernelcad export stl|step|dxf|3mf|glb -o ) executes them via an OpenCASCADE WASM kernel.