Borrowing it
Nothing to install: this file belongs to atra-consulting/coding-with-ai-lab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/atra-consulting/coding-with-ai-lab/main/.claude/agents/shell-reviewer.mdgit clone --depth 1 https://github.com/atra-consulting/coding-with-ai-labWrote 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/agents/atra-consulting/coding-with-ai-lab/shell-reviewer)<a href="https://agentmods.dev/agents/atra-consulting/coding-with-ai-lab/shell-reviewer"><img src="https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/shell-reviewer/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/agents/atra-consulting/coding-with-ai-lab/shell-reviewer"><img src="https://agentmods.dev/badge/agents/atra-consulting/coding-with-ai-lab/shell-reviewer.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 | $0.00397 | $0.01912 |
| Opus 5.5 | $0.00159 | $0.00765 |
| Sonnet 5.5 | $0.00079 | $0.00382 |
| Haiku 4.5 | $0.00040 | $0.00191 |
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 2mo 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 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 ''),dateflags,stat,readlink,grep -P,findoptions,cp/mvflags,awkbehavior - 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,md5sumvsmd5,sha256sumvsshasum -a 256differ 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:readwithout-t timeouton a pipe or tty that may never produce input while truewithout 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/wgetwithout timeouts:--connect-timeoutand--max-timemissingsshwithoutBatchModeor timeout: Interactive prompts that hang in non-interactive contextsgitoperations that may wait for credentialsflockor lock files that are never released on failure- Waiting on background jobs (
wait) without timeout or exit condition
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.
- 2mo ago First seen · 101 lines · 397 tokens per session scan A 203f9d136603
shell-reviewer is an agent published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 8d ago), licensed MIT. It adds 397 tokens to every session and 1,912 once invoked, about $0.0016 per session on Opus 5.5. 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…