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-investigategit 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-investigate)<a href="https://agentmods.dev/skills/karellen/karellen-lsp-mcp/lsp-investigate"><img src="https://agentmods.dev/badge/skills/karellen/karellen-lsp-mcp/lsp-investigate/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-investigate"><img src="https://agentmods.dev/badge/skills/karellen/karellen-lsp-mcp/lsp-investigate.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 | $0.00045 | $0.01663 |
| Opus 5 | $0.00023 | $0.00831 |
| Sonnet 5 | $0.00009 | $0.00333 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
lsp-investigate 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LSP Code Investigation
Use this skill when you need to understand code structure, trace bugs through call chains, find all usages of a symbol, or check compiler diagnostics across a codebase.
Prerequisites
karellen-lsp-mcpmust be installed and on PATH- An LSP server for the target language on PATH:
- 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]
- C/C++:
Workflow
1. Register the Project
Optionally scan first to see what languages are present:
lsp_scan_languages(project_path="/path/to/project")
Then register:
lsp_register_project(project_path="/path/to/project")
Auto-detection identifies the language, build system, and LSP server configuration.
See /karellen-lsp-mcp:lsp-register for detailed registration options.
2. Understand a Symbol
Start with hover to get the type signature without reading the file:
lsp_hover(project_id="<id>", file_path="/path/to/file.cpp", line=42, character=10)
Then jump to the definition, declaration, or type definition:
lsp_read_definition(project_id="<id>", file_path="/path/to/file.cpp", line=42, character=10)
lsp_read_declaration(project_id="<id>", file_path="/path/to/file.cpp", line=42, character=10)
lsp_read_type_definition(project_id="<id>", file_path="/path/to/file.cpp", line=42, character=10)
3. Trace Usage and Impact
Find all references or implementations:
lsp_find_references(project_id="<id>", file_path="/path/to/file.cpp", line=42, character=10)
lsp_find_implementations(project_id="<id>", file_path="/path/to/file.java", line=10, character=14)
Search for symbols by name across the project:
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 · 175 lines · 45 tokens per session scan A c36d5126dbe0
lsp-investigate is a skill published in the GitHub repository karellen/karellen-lsp-mcp (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,663 once invoked, about $0.0002 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
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
deadeye-sweep
Applies the findings from /deadeye-review, /deadeye-pr, and /deadeye-guard, verifies the build, and re-scans on a loop until nothing (critical/high, or every severity with --all) survives. In --pr mode also answers the PR's own open review comments, replying and resolving.
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…
vet
Thorough codebase investigation that finds and fixes real problems. Maps architecture, scans every layer (structural, correctness, security, reliability, performance, hygiene), prioritized report with evidence, fix plan, executes collaboratively. A senior engineer doing a full review with authority to fix. Use when…
daily-prevention
Use this skill to help a developer keep day-to-day code simple, maintainable, and robust — through automatable prevention (linters, type checkers, static analysis, and — for what static analysis structurally can't catch — AI-assisted review skills) rather than after-the-fact fixes. Trigger on "how do I keep this…