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.
npx skills add Miaoge-Ge/coding-agent-skills --skill bash-scripting-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skillsWrote 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/skills/miaoge-ge/coding-agent-skills/bash-scripting-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/bash-scripting-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/bash-scripting-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.
<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/bash-scripting-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/bash-scripting-expert.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 | $0.00082 | $0.01073 |
| Opus 5.5 | $0.00033 | $0.00429 |
| Sonnet 5.5 | $0.00016 | $0.00215 |
| Haiku 4.5 | $0.00008 | $0.00107 |
Grade A, and why
bash-scripting-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash Scripting Expert
Scripts fail in production on the input you didn't quote. Start strict, quote everything, clean up on exit, and run ShellCheck. When logic gets complex (JSON, data structures), switch to a real language.
When to Use
- Writing or debugging a Bash/POSIX shell script or CI/automation glue.
- "Works until a path has a space/newline" bugs; word-splitting, globbing, quoting.
- Argument parsing, exit codes, error handling, temp files, cleanup.
When NOT to Use
- Complex data/JSON/HTTP logic →
python-expert(shell is the wrong tool). - PowerShell scripting → use PowerShell tooling.
- CI pipeline YAML →
github-master.
Core Principles
1. Strict mode, every script
#!/usr/bin/env bash+set -euo pipefail: exit on error, error on unset vars, fail on any pipeline stage. SetIFS=$'\n\t'to stop surprise word-splitting on spaces.- Know
set -e's gotchas: it's suppressed insideif/||/&&conditions and command substitutions — check critical commands explicitly when needed.
2. Quote everything
- Always
"$var","${arr[@]}","$@"(not$*). Unquoted expansions split onIFSand glob — the #1 source of bugs. - Use
[[ … ]]for tests (not[ … ]),$(…)not backticks,(( … ))for arithmetic, andlocalfor all function variables.
3. Errors, cleanup, and exit codes
trap 'cleanup' EXITto remove temp files even on failure/interrupt. Create temps withmktemp.- Validate args and required commands up front; print usage to stderr and
exitnon-zero on misuse. Exit codes are meaningful —0success, non-zero failure. - Send errors/logs to
stderr(>&2); keepstdoutfor real output so the script composes in pipes.
4. Robust file & data handling
printfoverechofor anything with escapes/variables. Use--before paths, andfind … -print0 | while IFS= read -r -d ''for filenames with spaces/newlines.- For POSIX
sh, avoid bashisms ([[, arrays,local); if you use them, declarebashin the shebang. Lint with ShellCheck and format withshfmt.
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.
- 1mo ago First seen · 82 lines · 82 tokens per session scan A 90e2c33c718c
bash-scripting-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 1,073 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
lean
Dense answers: cut filler, keep substance. Prose only compression, Laravel/PHP aware. Open REFERENCE.md only when asked how lean decides.
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
ultracite
Ultracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project, or migrating its existing lint and format config onto Ultracite (ultracite init), (2) Running linting or formatting commands (check, fix, doctor), (3) Writing or…