setup

An interactive setup command for a Bash and shell-script development environment. It installs a language server, ShellCheck for finding shell-script problems, and shfmt for formatting shell code.

In plain words
What is it for?
Use it to install and verify Bash development tools, enable language-server support in Claude Code, and test linting and formatting on a shell script.
Why use it?
It gathers the required tools and checks their versions in one setup flow. This helps an agent or developer get code checking and editor support working consistently.

Command

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 commands/zircote/bash-lsp/setup
Clone the repo
git clone --depth 1 https://github.com/zircote/bash-lsp
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 269 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 $0.00008 $0.00269
Opus 5 $0.00004 $0.00134
Sonnet 5 $0.00002 $0.00054
Haiku 4.5 $0.00001 $0.00027

Measured yesterday against content hash 8c8297a1a6d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

commands/setup.md · 74 lines

What it actually says

Bash LSP Setup

This command will configure your Bash/Shell development environment with bash-language-server and essential tools.

Prerequisites Check

First, verify Node.js is installed:

node --version
npm --version

Installation Steps

1. Install bash-language-server

npm install -g bash-language-server

2. Install Development Tools

# Linting
brew install shellcheck

# Formatting
brew install shfmt

3. Verify Installation

bash-language-server --version
shellcheck --version
shfmt --version

4. Enable LSP in Claude Code

export ENABLE_LSP_TOOL=1

Verification

Test the LSP integration:

# Create a test file
cat > test_lsp.sh << 'EOF'
#!/bin/bash
greet() {
    local name="$1"
    echo "Hello, $name!"
}
greet "World"
EOF

# Run ShellCheck
shellcheck test_lsp.sh

# Run shfmt
shfmt -w test_lsp.sh

# Clean up
rm test_lsp.sh
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. yesterday First seen · 74 lines · 8 tokens per session scan A 8c8297a1a6d3

Subscribe to this mod's changes

setup is a command published in the GitHub repository zircote/bash-lsp (2 stars, last pushed 22d ago), licensed MIT. It adds 8 tokens to every session and 269 once invoked, about $0.0000 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.