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/hessesian/kmp-lsp/copilot-skillnpx skills add Hessesian/kmp-lsp --skill copilot-skillgit clone --depth 1 https://github.com/Hessesian/kmp-lspWrote 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/hessesian/kmp-lsp/copilot-skill)<a href="https://agentmods.dev/skills/hessesian/kmp-lsp/copilot-skill"><img src="https://agentmods.dev/badge/skills/hessesian/kmp-lsp/copilot-skill.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 | $0.00114 | $0.03323 |
| Opus 5 | $0.00057 | $0.01662 |
| Sonnet 5 | $0.00023 | $0.00665 |
| Haiku 4.5 | $0.00011 | $0.00332 |
Grade A, and why
kmp-lsp 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 today.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kmp-lsp — Capabilities & Limitations
⚠️ Prerequisite: Experimental mode required
The lsp tool is only available when Copilot CLI is started with copilot --experimental (or --exp).
Without it, the LSP tool does not appear and kmp-lsp will not be connected.
If you see no lsp tool available, ask the user to restart with copilot --experimental.
You have access to a Kotlin/Java/Swift LSP server (kmp-lsp) via the lsp tool.
Language support
- Kotlin / Java — full support: indexing, hover, goToDefinition, workspaceSymbol, goToImplementation, findReferences, rename
- Swift — structural support: documentSymbol (immediate), hover (property types), goToDefinition (cross-module); no type inference (no sourcekit-lsp backend)
Indexing & Readiness
The server indexes files in the background on startup. Before using workspaceSymbol, always call kmp_lsp_status to check if indexing is complete.
- Cold index (no cache): 30–70s depending on project size
- Warm start (from cache): 1–3s
- Progress shown in editor (0% → live % every 500ms → done)
Cold-start navigation: documentSymbol, hover, and goToDefinition work immediately on any opened file — the current file is indexed on-demand before symbol lookup. workspaceSymbol requires full indexing.
Cache staleness: cache version bump triggers a full re-index automatically. A "Cache deserialize failed" warning means a one-time re-index is occurring.
Workspace root auto-detection
When no config file is set, did_open detects the workspace root using tiered marker priority:
- Strong markers (nearest wins):
settings.gradle.kts,build.gradle,pom.xml,Cargo.toml— subproject root in a mono-repo .git— repo root; wins over weak markers- Weak markers:
Package.swift— last resort (present at every Swift module, not reliable as root)
This correctly handles mono-repos (e.g. android/settings.gradle.kts beats monorepo .git) and Swift mono-repos (e.g. ios/.git beats nested ios/Modules/*/Package.swift).
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.
- today First seen · 181 lines · 114 tokens per session scan A 4cded7570ab2
kmp-lsp is a skill published in the GitHub repository Hessesian/kmp-lsp (180 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 3,323 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kmp-repositories
Repository pattern for Kotlin Multiplatform. Shared interfaces with platform-specific implementations, clean data layer architecture.
expect-actual
Kotlin Multiplatform expect/actual patterns for platform-specific APIs. Learn to declare shared interfaces with platform implementations.
shared-coroutines
Shared coroutines configuration for Kotlin Multiplatform. Platform dispatchers, Flow sharing, and common scope patterns.
shared-models
Shared data models for Kotlin Multiplatform using kotlinx.serialization. Cross-platform domain models with validation and serialization.