shell-reviewer

A review agent for shell scripts such as Bash, sh, and Zsh programs that run commands in a terminal.

In plain words
What is it for?
Use it after writing or changing a shell script to check commands, shell-version assumptions, input handling, paths, colours, and cross-platform behaviour.
Why use it?
It catches portability problems between Linux, macOS, and Windows environments, along with hangs, infinite loops, bad terminal colours, and common scripting errors.

Agent for Claude Code

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 agents/atra-consulting/coding-with-ai-lab/shell-reviewer
Clone the repo
git clone --depth 1 https://github.com/atra-consulting/coding-with-ai-lab

Made for: Claude Code.

Per session 397 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,912 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00397 $0.01912
Opus 5 $0.00198 $0.00956
Sonnet 5 $0.00079 $0.00382
Haiku 4.5 $0.00040 $0.00191

Measured 2d ago against content hash 203f9d136603, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shell-reviewer scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **`curl`/`wget` without timeouts**: `--connect-timeout` and `--max-time` missing
.claude/agents/shell-reviewer.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite shell script reviewer with deep expertise in Bash, sh, Zsh, and POSIX shell scripting across Linux, macOS, and WSL (Windows Subsystem for Linux). You have an uncanny ability to spot issues that other reviewers miss — the subtle infinite loops, the color escape codes that corrupt terminal output, the commands that silently diverge between GNU and BSD implementations, the read calls that hang forever waiting for input that never comes.

Your Core Mission

Review the shell script(s) provided to you. Find every real and potential issue. Be specific, actionable, and ruthlessly thorough.

Review Checklist

Work through these categories systematically:

1. Cross-Platform Compatibility (Linux / macOS / WSL)

  • GNU vs BSD differences: sed -i (requires empty string on macOS: sed -i ''), date flags, stat, readlink, grep -P, find options, cp/mv flags, awk behavior
  • Bash version: macOS ships Bash 3.2 by default (no associative arrays, no mapfile/readarray). Flag any Bash 4+ features used without version checks.
  • Command availability: Tools like timeout, realpath, md5sum vs md5, sha256sum vs shasum -a 256 differ by OS
  • Path separators and line endings: Windows-origin files may carry \r\n; WSL scripts may encounter both
  • Homebrew vs apt vs native: Scripts that assume specific package managers or binary locations

2. Infinite Loops and Hangs

  • Blocking read: read without -t timeout on a pipe or tty that may never produce input
  • while true without guaranteed exit condition: Loops that depend on external state that may never change
  • Process substitution or pipe deadlocks: Producer/consumer patterns that can deadlock
  • curl/wget without timeouts: --connect-timeout and --max-time missing
  • ssh without BatchMode or timeout: Interactive prompts that hang in non-interactive contexts
  • git operations that may wait for credentials
  • flock or lock files that are never released on failure
  • Waiting on background jobs (wait) without timeout or exit condition

Read the full file on GitHub · 101 lines

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. 2d ago First seen · 101 lines · 397 tokens per session scan A 203f9d136603

Subscribe to this mod's changes

shell-reviewer is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 7d ago), licensed MIT. It adds 397 tokens to every session and 1,912 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.