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 commands/zircote/lsp-tools/lsp-setupgit clone --depth 1 https://github.com/zircote/lsp-toolsWhat 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 | $0.00020 | $0.04535 |
| Opus 5 | $0.00010 | $0.02268 |
| Sonnet 5 | $0.00004 | $0.00907 |
| Haiku 4.5 | $0.00002 | $0.00453 |
Grade B, and why
lsp-setup scanned grade B with 1 finding 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 3d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
/lsp-tools:* for related commands How it starts
The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<help_check>
Help Check
If $ARGUMENTS contains --help or -h:
Output this help and HALT (do not proceed further):
<help_output>
LSP_SETUP(1) User Commands LSP_SETUP(1)
NAME
lsp-setup - Set up LSP hooks, verify servers, and configure CLAUDE.md
SYNOPSIS
/lsp-tools:lsp-setup [language...] [options]
DESCRIPTION
Complete LSP toolchain setup: detects languages (including Markdown and
Terraform), verifies LSP servers are installed, offers to install missing
servers, configures hooks, and updates CLAUDE.md with LSP guidance.
SPECIALIZED PLUGINS: If zircote/*-lsp plugins are installed (rust-lsp,
terraform-lsp, markdown-lsp), hooks for those languages are skipped since
the specialized plugins provide their own hooks.
OPTIONS
--help, -h Show this help message
--skip-install Skip LSP server installation prompts
--skip-hooks Skip hooks installation
--skip-claudemd Skip CLAUDE.md modifications
--verify-only Only verify LSP servers, don't install anything
LANGUAGES
TypeScript/JavaScript, Python, Go, Rust, Java, Kotlin, C/C++, C#,
PHP, Ruby, HTML/CSS, LaTeX, Markdown, Terraform
SPECIALIZED PLUGINS (hooks provided by plugin, not lsp-tools)
zircote/rust-lsp 16 hooks (clippy, security, dependencies)
zircote/terraform-lsp 17 hooks (tflint, trivy, checkov, terragrunt)
zircote/markdown-lsp 4 hooks (links, frontmatter, code blocks, syntax)
EXAMPLES
/lsp-tools:lsp-setup Auto-detect and full setup
/lsp-tools:lsp-setup typescript python Setup specific languages
/lsp-tools:lsp-setup --verify-only Check LSP server status
/lsp-tools:lsp-setup --skip-install Setup hooks only
SEE ALSO
/lsp-tools:* for related commands
LSP_SETUP(1)
</help_output>
After outputting help, HALT immediately. Do not proceed with command execution. </help_check>
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.
- 3d ago First seen · 534 lines · 20 tokens per session scan B 98810cc5f3f8
lsp-setup is a command published in the GitHub repository zircote/lsp-tools (12 stars, last pushed 23d ago), licensed MIT. It adds 20 tokens to every session and 4,535 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
rb-setup
First-time setup. Configure the LLM API key, or a no-API-key local host runner (Codex / Trae / Claude / any headless CLI) that RepoBrain uses for codebase Q&A and refresh. / 首次 setup，配置 RepoBrain 代码问答与 refresh 所需的 LLM API key，或无需 API key 的本地 host runner（Codex / Trae / Claude / 任意无头 CLI）。.
rb-ask
Ask a question about the current project's codebase via the repobrain knowledge hub. / 通过 repobrain 知识库询问当前项目代码。.
rb-refresh
Rebuild the repobrain project knowledge base after significant changes. / 在重要改动后重建 repobrain 项目知识库。.
rb-init
Scaffold a new multi-agent repository from the RepoBrain template (invokes agent-repo-init skill). / 基于 RepoBrain 模板创建新的多智能体仓库。.
ask
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
export
Export the wiki (or architecture model) to markdown, HTML, JSON, or Structurizr DSL.