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.
git clone --depth 1 https://github.com/imgompanda/fireautoWrote 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/commands/imgompanda/fireauto/lsp-install)<a href="https://agentmods.dev/commands/imgompanda/fireauto/lsp-install"><img src="https://agentmods.dev/badge/commands/imgompanda/fireauto/lsp-install/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/commands/imgompanda/fireauto/lsp-install"><img src="https://agentmods.dev/badge/commands/imgompanda/fireauto/lsp-install.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 | $0.00018 | $0.01696 |
| Opus 5.5 | $0.00007 | $0.00678 |
| Sonnet 5.5 | $0.00004 | $0.00339 |
| Haiku 4.5 | $0.00002 | $0.00170 |
Grade B, and why
lsp-install 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` 파일을 읽어서 `env` 섹션에 `ENABLE_LSP_TOOL`이 있는지 확인하세요. How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fireauto-lsp: Claude Code LSP 원클릭 셋업
Claude Code에 LSP(Language Server Protocol)를 연결해서 코드 탐색 속도와 정확도를 극대화하는 커맨드예요.
모든 출력은 **한국어(토스체)**로 작성해요.
LSP가 뭔지 간단히 설명
Claude Code는 기본적으로 코드를 찾을 때 **텍스트 검색(grep)**을 써요. LSP를 켜면 VS Code의 "정의로 이동(Ctrl+Click)"처럼 코드 구조를 이해하면서 찾아요.
- 속도: 수십 초 → 50ms
- 정확도: 비슷한 단어 → 정확한 호출 계층
- 에러 감지: 편집 직후 타입 에러 즉시 포착
- 토큰 절약: 엉뚱한 파일 안 읽으니까 비용도 절약
Step 1: 어떤 개발을 하시나요?
먼저 사용자에게 개발 분야를 물어보세요. 초보자도 쉽게 고를 수 있도록 선택지를 보여줘요:
어떤 개발을 하고 계세요? (번호로 골라주세요, 여러 개 가능!)
1. 웹 개발 (React, Next.js, Vue 등)
2. 백엔드 개발 (Python, Go, Java 등)
3. iOS/macOS 앱 개발 (Swift)
4. 안드로이드 앱 개발 (Kotlin)
5. 시스템/임베디드 (C/C++, Rust)
6. 게임 개발 (C#/Unity)
7. 잘 모르겠어요 (프로젝트 자동 감지해줘!)
선택에 따라 설치할 항목을 매핑하세요:
| 선택 | 설치되는 LSP | 설치 명령 | 플러그인 |
|---|---|---|---|
| 1. 웹 개발 | typescript-language-server | npm i -g typescript-language-server typescript |
typescript-lsp |
| 2. 백엔드 (Python) | pyright | npm i -g pyright |
pyright-lsp |
| 2. 백엔드 (Go) | gopls | go install golang.org/x/tools/gopls@latest |
gopls-lsp |
| 2. 백엔드 (Java) | jdtls | brew install jdtls |
jdtls-lsp |
| 2. 백엔드 (PHP) | intelephense | npm i -g intelephense |
php-lsp |
| 3. iOS/macOS | sourcekit-lsp | (Xcode에 포함) | swift-lsp |
| 4. 안드로이드 | kotlin-language-server | brew install kotlin-language-server |
kotlin-lsp |
| 5. 시스템 (C/C++) | clangd | brew install llvm |
clangd-lsp |
| 5. 시스템 (Rust) | rust-analyzer | rustup component add rust-analyzer |
rust-analyzer-lsp |
| 6. 게임 (C#) | csharp-ls | dotnet tool install -g csharp-ls |
csharp-lsp |
"7. 잘 모르겠어요"를 선택한 경우
프로젝트 루트에서 Glob으로 아래 파일들을 자동 감지하세요:
| 감지 파일 | 언어 |
|---|---|
tsconfig.json, package.json |
TypeScript/JS |
requirements.txt, pyproject.toml, *.py |
Python |
go.mod |
Go |
Cargo.toml |
Rust |
Package.swift, *.xcodeproj |
Swift |
pom.xml, build.gradle |
Java |
*.csproj, *.sln |
C# |
composer.json |
PHP |
CMakeLists.txt + *.c/*.cpp |
C/C++ |
build.gradle.kts + *.kt |
Kotlin |
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.
- 1mo ago First seen · 183 lines · 18 tokens per session scan B 7f6364c0ff4e
lsp-install is a command published in the GitHub repository imgompanda/fireauto (140 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 1,696 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
incident
Live incident response — intake a Sentry issue, stack trace, or symptom; gate mitigate-first vs root-cause-first; keep a UTC timeline. Use when production is broken RIGHT NOW; for the after-action write-up alone, use /orc:postmortem.
debug
Systematic root-cause investigation, then fix with TDD — never proposes a fix before finding the cause; resumable diagnosis + regression test in .orc/ state. Workspace-aware. For a quick one-off look without session state, prefer the bundled /debug.
ci-readout
Generate a comprehensive summary of recent CI runs and failing jobs.
quality-gate
Run formatter, linter, and type checks for a file or directory. Report remediation steps.
ci
Diagnose and fix a red CI run — dispatches orc-ci-investigator, then routes on its verdict: auto-fix via orc-code-fixer, flake re-run, infra escalation, or /orc:debug hand-off. Use when CI is red, PR checks fail, or after a push with --watch.
t800-loop
A semi-manual workflow for reviewing the results of a previous development run and preparing a queue of fixes. HITL means a human reviews or approves the queued work before fixes are applied in batches.