ai-context-engineering-for-qa: Skill for Claude Code

.claude/skills/bash-reviewer/SKILL.md

bash-reviewer is a skill for Claude Code from vlad-ryzhkov/ai-context-engineering-for-qa. It costs 68 tokens per session (2,980 once invoked), scanned A, original, Unlicense.

A shell-script review checks Bash or other shell files for security, portability, reliability, and repeated code. It reports problems in a structured format and can suggest fixes with documentation references.

In plain words
What is it for?
It is for auditing .sh and .bash files before merging, during troubleshooting, or when hardening scripts used in automation.
Why use it?
It helps find shell-specific failures and unsafe patterns that may work on one machine but break in another or expose commands to unwanted input.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

This is vlad-ryzhkov/ai-context-engineering-for-qa's own configuration. It tells Claude Code how to work on ai-context-engineering-for-qa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-context-engineering-for-qa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vlad-ryzhkov/ai-context-engineering-for-qa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vlad-ryzhkov/ai-context-engineering-for-qa/main/.claude/skills/bash-reviewer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qa

Made for: Claude Code.

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.

agentmods badge for bash-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/bash-reviewer/github.svg)](https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/bash-reviewer)
Your own site
<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/bash-reviewer"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/bash-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.

agentmods 80×15 button for bash-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/bash-reviewer"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/bash-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,980 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.02980
Opus 5 $0.00034 $0.01490
Sonnet 5 $0.00014 $0.00596
Haiku 4.5 $0.00007 $0.00298

Measured yesterday against content hash 084942b88dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bash-reviewer 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.

.claude/skills/bash-reviewer/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bash-reviewer — Shell Script Anti-Pattern Reviewer

SILENT MODE: Execute all analytical phases silently. Do not output intermediate reasoning, progress updates, or conversational filler. Output ONLY the structured issue blocks and summary. Exception: if no issues found, output a single line: ✅ No anti-patterns detected


When to Use

  • User asks to review, audit, or check shell scripts for quality
  • Before merging PRs that add or modify .sh files
  • When diagnosing flaky or platform-dependent script failures
  • When hardening scripts that run in CI/CD pipelines

When NOT to Use

  • Python, Ruby, Go, or other non-shell scripts
  • GitHub Actions YAML — use /workflow-expert instead
  • Issues already caught by shellcheck (quoting, SC2068, SC2086)
  • One-liner shell commands in Makefiles or Dockerfiles

Scope

DO review:

  • .sh and .bash files
  • Security: eval injection, unvalidated command expansion
  • Portability: sed -i, grep -P, readarray/mapfile, find -o precedence
  • Robustness: division by zero, wc in arithmetic, missing prerequisite checks, set -euo pitfalls
  • DRY: repeated check/counter blocks, duplicated scan loops, shared constants across files

DON'T review:

  • Style preferences (indentation, naming conventions)
  • ShellCheck-detectable issues (quoting, word splitting)
  • Logic correctness of the script's business domain

Detection Workflow

Step 1: Discover Scripts

Use Glob to find all .sh and .bash files in the target path. If user specified a single file, skip discovery.

Step 2: Scan for Anti-Patterns

For each script, use Grep to scan for pattern signatures:

Signal Grep Pattern Category
eval eval\s Security
$command used as execution ^\s*\$\w+ Security
sed -i sed\s+-i Portability
grep -P grep\s+.*-P Portability
readarray / mapfile readarray|mapfile Portability
find with -o find\s.*-o\s Portability
Division in arithmetic \$((.*/.*) Robustness
wc -l in arithmetic context wc\s+-l Robustness
set -.*u with arrays set\s+-.*u Robustness
pipefail with grep pipefail Robustness
Tool usage without guard jq|yq|shellcheck|docker|kubectl Robustness
Inverted return codes return 0.*fail|return 0.*error Robustness
set -e in WARN-only script set -.*e.*pipefail Robustness
Variable as regex in grep grep ".*\$\w|grep \$\{ Security
Relative symlink in hooks ln -s .*\.\./ Robustness
sed for YAML/JSON parsing sed.*---.*---|sed.*^[a-z]*: Robustness
CLI arg into path w/o guard --\w+.*"\$2".*|\$\{[A-Z_]+\}/\$\{ Security
Substring placeholder-exclude your_|example_|placeholder Security
Case-restricted security cls \[A-Z_\].*(TOKEN|KEY|SECRET) Security
Text-only extension filter find.*-name.*\.md.*-o.*-name.*\.sh Security
Suppression w/o allowlist is_nolint|is_suppressed|# noqa Security
Repeated check+counter block check_result=\$\? DRY
Repeated scan/grep loop while.*read.*grep.*done DRY
Repeated format+counter \(\(.*\+\+\)\).*|| true DRY
Duplicated constants/utils RED=.*033 in multiple files DRY
Missing shellcheck source source.*\.sh Robustness

Read the full file on GitHub · 228 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. yesterday Changed · +5 lines 084942b88dbd
  2. 10d ago First seen · 223 lines · 68 tokens per session scan A 99e3d3c3838f

Subscribe to this mod's changes

bash-reviewer is a skill published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed today), licensed Unlicense. It adds 68 tokens to every session and 2,980 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

effective-kotlin

Apply Effective Kotlin best practices (Marcin Moskała, 2nd Ed). Covers Safety (Items 1-10: mutability, scope, nulls, types, expectations, errors, resources, tests), Readability (Items 11-18: operators, receivers, properties, naming), Reusability (Items 19-25: DRY, generics, delegation, variance), Abstraction (Items…

booklib-ai/booklib · 212 tokens

cat:stakeholder-review

Multi-perspective quality review gate with architect, security, quality, tester, and performance stakeholders.

cowwoc/cat · 24 tokens

render-diff

MANDATORY: Use BEFORE showing ANY diff to user - transforms git diff into 4-column table with box characters (╭╮╰╯│). Required for approval gates, code reviews, change summaries.

cowwoc/cat · 48 tokens

debriefing-code-changes

Debriefs a developer after an AI-assisted coding session by inspecting git diffs or commits, explaining the actual architecture decisions, design patterns, tradeoffs, caveats, and learning concepts with file/function references, then generating a practical quiz and follow-up study notes. Use when the user says they…

Agent-Engineer-Master/skill-engineer · 128 tokens

swarm-pr-review

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

ZaxbyHub/opencode-swarm · 91 tokens

review

Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.

automagik-dev/genie · 29 tokens