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/l3utterfly/layla-sdk/layla-sdknpx skills add l3utterfly/layla-sdk --skill layla-sdkgit clone --depth 1 https://github.com/l3utterfly/layla-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/l3utterfly/layla-sdk/layla-sdk)<a href="https://agentmods.dev/skills/l3utterfly/layla-sdk/layla-sdk"><img src="https://agentmods.dev/badge/skills/l3utterfly/layla-sdk/layla-sdk.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 | $0.00205 | $0.09238 |
| Opus 5 | $0.00102 | $0.04619 |
| Sonnet 5 | $0.00041 | $0.01848 |
| Haiku 4.5 | $0.00020 | $0.00924 |
Grade A, and why
layla-sdk 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 yesterday.
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 — 1,007 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layla SDK
Use @layla-network/sdk when building a third-party Layla mini-app that runs inside the Layla WebView and needs to call the on-device Layla host.
The packaged skill is self-contained. Use the bundled references first:
- Read
references/sdk-api.mdfor SDK imports, method signatures, examples, exported types, mock usage, abort behavior, and error handling. - Read
references/mini-apps-overview.mdfor mini-app packaging, metadata,index.htmlversusindex.url, WebView runtime expectations, and troubleshooting.
If the bundled reference appears stale and internet access is available, check the public package source or release docs for the installed package version:
https://github.com/l3utterfly/layla-sdk- Prefer tagged release source over the default branch when the user's project has a specific installed version.
Runtime Rules
Run SDK calls inside the Layla WebView. The host injects the React Native WebView bridge. If that bridge is unavailable, SDK requests reject with LaylaBridgeUnavailableError.
The one non-WebView environment is task.js: an optional background task script at the mini-app root that the host runs in a QuickJS runtime with the SDK already injected as a global layla instance. See "Background Tasks (task.js)" below.
Do not use this SDK as an ordinary browser HTTP client. There is no API key, base URL, or fetch endpoint to configure. The SDK sends bridge messages to the Layla host.
Layla SDK is designed to work with local LLMs running on device, so response times can be slow. When building mini-apps, prioritize streaming APIs and show appropriate loading, thinking, and progress states instead of leaving the UI idle while a request runs.
For local browser development outside Layla, use installLaylaMock(...) before the first SDK call when the app needs SDK responses during development.
Core Import
Import from the package root:
import LaylaSDK, {
Layla,
LaylaAbortError,
LaylaBridgeUnavailableError,
LaylaError,
type ChatCompletionMessageParam,
type LaylaChatMessage,
type LaylaChatHistoryEntry,
type LaylaScheduledChatMessage,
type LaylaCharacter,
type LaylaMemory,
type LaylaPersona,
type LaylaTTSVoice,
type GenerateVoiceToFileResult,
type ExecuteSqlResult,
type STTSpeechRecognizedListener,
type BackgroundAudioStatusListener,
type BackgroundAudioTrackChangedListener,
type BackgroundAudioFinishedListener,
type LaylaExecutionContext,
type ChatContextFinishedSpeakingListener,
type ChatContextNewMessageListener,
type ChatContextSentimentUpdateListener,
type ChatContextStartedSpeakingListener,
type ChatContextStartedThinkingListener,
type SentimentValues,
type TavernCardV2,
} from '@layla-network/sdk';
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.
- yesterday Changed · +63 lines · +20 tokens per session 53c58ce18937
- 5d ago First seen · 944 lines · 185 tokens per session scan A b413b9cbeb58
layla-sdk is a skill published in the GitHub repository l3utterfly/layla-sdk (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 205 tokens to every session and 9,238 once invoked, about $0.0010 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…