agentmods.dev

lsp-maintain

lsp-maintain is a skill for Claude Code, Codex from shareAI-lab/Kode-CLI. It costs 67 tokens per session (560 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for configuring and diagnosing language servers in Kode. Language servers provide code features such as diagnostics, completion, and navigation.

In plain words
What is it for?
Use it to inspect LSP status, configure servers through plugins or files, and align Kode's behaviour with its reference command-line tool.
Why use it?
It helps explain missing or disabled language features by checking the actual configured servers and plugin-based settings.

Skill for Claude CodeCodex

not rated 5.2k +2 6d ago A scan 67 tokens original Apache-2.0
View the source file shareAI-lab/Kode-CLI
Install

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.

agentmods
npx agentmods add skills/shareai-lab/kode-cli/lsp-maintain
Any agent
npx skills add shareAI-lab/Kode-CLI --skill lsp-maintain
Clone the repo
git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for lsp-maintain

README.md
[![agentmods](https://agentmods.dev/badge/skills/shareai-lab/kode-cli/lsp-maintain.svg)](https://agentmods.dev/skills/shareai-lab/kode-cli/lsp-maintain)
Your own site
<a href="https://agentmods.dev/skills/shareai-lab/kode-cli/lsp-maintain"><img src="https://agentmods.dev/badge/skills/shareai-lab/kode-cli/lsp-maintain.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00067 $0.00560
Opus 5 $0.00034 $0.00280
Sonnet 5 $0.00013 $0.00112
Haiku 4.5 $0.00007 $0.00056

Measured 4d ago against content hash 5d0c11cb1ff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lsp-maintain 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 4d 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.

packages/builtin-skills/skills/lsp-maintain/SKILL.md · 51 lines

What it actually says

LSP Maintain (Reference-aligned)

Non-negotiables (policy)

  • Do not respond with menu-style instructions like “run /lsp-maintain install” or “run /lsp-maintain doctor”.
  • Prefer executing capability changes through SlashCommand (e.g. /plugin ..., /lsp) or Edit to configuration files.
  • Keep the conversation focused: only load deeper resources if absolutely necessary.

What “LSP enabled” means in Kode

Kode’s LSP tool is enabled only when there is at least one resolved LSP server and at least one is not in error.

Step 1 — Establish facts (no guessing)

  1. Ask for the user goal (languages, monorepo vs single package, whether they already use plugins).
  2. Run /lsp via SlashCommand and read the “Configured servers” list.
  3. If there are zero servers, conclude: no LSP servers are configured (do not speculate about missing binaries).

Step 2 — Identify configuration source (plugin-only)

Kode resolves LSP servers from enabled plugins:

  • Plugin root .lsp.json (JSON, top-level record)
  • Plugin manifest field lspServers (inline record or relative file path within plugin root)

If the user needs a new server, the correct path is: enable a plugin that provides it, or add/update a plugin’s .lsp.json.

Step 3 — Apply changes through agent CLI

Prefer:

  • Use SlashCommand to manage plugins (/plugin ...) and re-check with /lsp.
  • Use Edit to update the plugin’s .lsp.json or manifest lspServers record/file.

Step 4 — Verify

  1. Re-run /lsp and confirm servers are resolved.
  2. Attempt one LSP tool call (e.g. goToDefinition) on a file extension that is mapped in extensionToLanguage.

Notes for LSP server config authoring

  • command must be an executable (avoid embedding arguments; use args).
  • Kode runs servers using stdio pipes.
  • Do not use restartOnCrash, startupTimeout, or shutdownTimeout in the config (Kode treats them as unsupported).
Changes

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.

  1. 4d ago First seen · 51 lines · 67 tokens per session scan A 5d0c11cb1ff9

Subscribe to this mod's changes

lsp-maintain is a skill published in the GitHub repository shareAI-lab/Kode-CLI (5,212 stars, last pushed 6d ago), licensed Apache-2.0. It adds 67 tokens to every session and 560 once invoked, about $0.0003 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.

Debugging
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens