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 karellen/karellen-lsp-mcp --skill lsp-registergit clone --depth 1 https://github.com/karellen/karellen-lsp-mcpWrote 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/karellen/karellen-lsp-mcp/lsp-register)<a href="https://agentmods.dev/skills/karellen/karellen-lsp-mcp/lsp-register"><img src="https://agentmods.dev/badge/skills/karellen/karellen-lsp-mcp/lsp-register/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/karellen/karellen-lsp-mcp/lsp-register"><img src="https://agentmods.dev/badge/skills/karellen/karellen-lsp-mcp/lsp-register.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.01763 |
| Opus 5 | $0.00028 | $0.00881 |
| Sonnet 5 | $0.00011 | $0.00353 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
lsp-register 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LSP Project Registration
Use this skill to register a project for LSP-backed code intelligence. Once registered,
all lsp_* query tools become available for that project.
Prerequisites
karellen-lsp-mcpmust be installed and on PATH- An LSP server for the target language:
- C/C++:
clangd— install viapip install --user karellen-lsp-mcp[clangd]or system package manager - Java/Kotlin:
jdtls— install viapip install --user karellen-lsp-mcp[jdtls] - Python:
pyright— install viapip install --user karellen-lsp-mcp[pyright] - Rust:
rust-analyzer— install viarustup component add rust-analyzer - All servers:
pip install --user karellen-lsp-mcp[all] - Other languages: any LSP server, specified via
lsp_command
- C/C++:
Workflow
1. Scan or Detect the Project (Optional)
Quick scan — count file extensions and see what languages are present:
lsp_scan_languages(project_path="/path/to/project")
Full detection — analyze build systems, IDE metadata, and configuration:
lsp_detect_project(project_path="/path/to/project")
Both return language recommendations without registering anything. Use scan for a quick overview, detect for build system details and configuration.
2. Register the Project
Auto-Detection (Recommended)
Omit the language parameter to let the server auto-detect:
lsp_register_project(project_path="/path/to/project")
Auto-detection scans for build system markers (CMakeLists.txt, build.gradle, pom.xml, pyproject.toml, Cargo.toml, etc.), IDE metadata (.idea/, .classpath, .vscode/), and source file conventions.
Explicit Language
Specify the language when auto-detection isn't sufficient:
lsp_register_project(project_path="/path/to/project", language="cpp")
C/C++ with compile_commands.json
For best results with clangd, provide the compile database location:
lsp_register_project(
project_path="/path/to/project",
language="cpp",
build_info={"compile_commands_dir": "/path/to/build"}
)
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 · 201 lines · 56 tokens per session scan A ae174d277a39
lsp-register is a skill published in the GitHub repository karellen/karellen-lsp-mcp (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,763 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 2026-08-31.
Other skills, from other repositories
code-standards
Language-agnostic code standards for writing clean, maintainable code. Covers modular design, functional patterns, error handling, security, and testing. Make sure to use this skill whenever writing, refactoring, or reviewing any code, even for quick fixes, prototypes, or single-file changes. This is the baseline for…
security-auditor
Adversarial security auditing workflow for source changes. Make sure to use this skill whenever reviewing code before merge, hunting for vulnerabilities, auditing dependencies, or assessing security exposure of new features, even if the user doesn't explicitly ask for a security review. Includes OWASP-focused scans…
cook
Handle engineering work in an active jeff project and drive its tracked task pipeline. Use when the Chef addresses Jeff, mentions jeff/cook, asks to set up, initialize, turn on, deinit, validate, or check status/tasks; runs cook, cook , or cook on ; wants to start or resume a task; asks to implement/build a plan (not…
openehr-assistant
This skill should be used when a conversation touches openEHR outside a task owned by a dedicated skill — e.g. "what is an archetype?", "how do openEHR templates work?", "which composition category fits this data?", "find me a guide on X", "where do I start with openEHR modeling?" — or names openEHR concepts (ADL…
template-authoring
This skill should be used when the user asks to "create a template", "design a template", "constrain archetypes into a template", "review a template", "categorise a dataset with CGEM", "should this be persistent, episodic or event?", "split this form across compositions", "sketch a template from this form / which…
archetype-authoring
This skill should be used when the user asks to "create", "edit", "specialize", "review / remediate", "write the rationale for", "translate / localise", or "fix the ADL syntax of" an openEHR archetype (including "this archetype won't parse / won't validate"), or to import a CKM archetype into the workspace for reuse.…