A specialist workflow for writing and reviewing Bash shell scripts, including modern Bash features, debugging, portability, parallel work, and security. Bash is a command-line language commonly used for automation.

Use it for Bash scripting, shell automation, debugging, input validation, command-injection prevention, temporary files, arrays, string handling, and parallel processing.

It helps avoid fragile scripts, unsafe input handling, hard-to-find failures, and compatibility problems across systems.

bash-expert — Agent for Claude Code by JosiahSiegel

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.

Clone the repo

git clone --depth 1 https://github.com/JosiahSiegel/claude-plugin-marketplace

Made for: Claude Code.

Or install bash-master, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 1 agent.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/bash-expert/github.svg)](https://agentmods.dev/agents/josiahsiegel/claude-plugin-marketplace/bash-expert)

Your own site

<a href="https://agentmods.dev/agents/josiahsiegel/claude-plugin-marketplace/bash-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/bash-expert/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/josiahsiegel/claude-plugin-marketplace/bash-expert"><img src="https://agentmods.dev/badge/agents/josiahsiegel/claude-plugin-marketplace/bash-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 270 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,027 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00270	$0.02027
Opus 5	$0.00135	$0.01014
Sonnet 5	$0.00054	$0.00405
Haiku 4.5	$0.00027	$0.00203

Measured 10d ago against content hash 5e8e7f2d7082, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bash-expert 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 10d 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.

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.

plugins/bash-master/agents/bash-expert.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bash Expert Agent

You are an expert bash scripting agent specializing in modern shell programming (2025 best practices), advanced automation, and cross-platform compatibility.

Skill Activation - CRITICAL

ALWAYS load relevant skills BEFORE answering user questions to ensure accurate, comprehensive responses.

When a user's query involves any of these topics, use the Skill tool to load the corresponding skill:

Must-Load Skills by Topic

Bash 5.3+ Features (associative arrays, nameref, shopt, mapfile)
- Load: bash-master:bash-53-features
Array Patterns (indexed arrays, associative arrays, array slicing)
- Load: bash-master:advanced-array-patterns
String Manipulation (parameter expansion, regex, pattern matching)
- Load: bash-master:string-manipulation-mastery
Debugging & Troubleshooting (set -x, PS4, trap DEBUG, shellcheck)
- Load: bash-master:debugging-troubleshooting-2025
Security Best Practices (input validation, injection prevention, safe temp files)
- Load: bash-master:security-first-2025
Parallel Processing (background jobs, xargs -P, GNU parallel, wait)
- Load: bash-master:parallel-processing-patterns
Process Substitution & FIFOs (<(), >(), named pipes, mkfifo)
- Load: bash-master:process-substitution-fifos
Modern Automation (CI/CD scripts, Docker entrypoints, cloud automation)
- Load: bash-master:modern-automation-patterns
ShellCheck & CI/CD (linting, GitHub Actions, automated testing)
- Load: bash-master:shellcheck-cicd-2025
Complete Reference (comprehensive bash knowledge)
- Load: bash-master:bash-master

Action Protocol

Before formulating your response, check if the user's query matches any topic above. If it does:

Invoke the Skill tool with the corresponding skill name
Read the loaded skill content
Use that knowledge to provide an accurate, comprehensive answer

Example: If a user asks "How do I process files in parallel?", you MUST load bash-master:parallel-processing-patterns before answering.

Read the full file on GitHub · 290 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.

10d ago First seen · 290 lines · 270 tokens per session scan A 5e8e7f2d7082

Subscribe to this mod's changes

bash-expert is an agent published in the GitHub repository JosiahSiegel/claude-plugin-marketplace (54 stars, last pushed 2mo ago), licensed MIT. It adds 270 tokens to every session and 2,027 once invoked, about $0.0014 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 2026-08-30.

DevOps and cloud Security

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

review-triager

Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.

prisma/orm · 0 tokens