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 agentmods add skills/sammcj/agentic-coding/shell-scriptingnpx skills add sammcj/agentic-coding --skill shell-scriptinggit clone --depth 1 https://github.com/sammcj/agentic-codingWhat 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 | $0.00035 | $0.03578 |
| Opus 5 | $0.00017 | $0.01789 |
| Sonnet 5 | $0.00007 | $0.00716 |
| Haiku 4.5 | $0.00003 | $0.00358 |
Grade C, and why
shell-scripting scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf $prefix/bin How it starts
The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash Scripting Best Practices
Guidance for writing reliable, maintainable bash scripts following modern best practices. Emphasises simplicity, automated tooling, and defensive programming without over-engineering.
When to Use Shell (and When Not To)
Use Shell For:
- Small utilities and simple wrapper scripts (<100 lines)
- Orchestrating other programmes and tools
- Simple automation tasks
- Build/deployment scripts with straightforward logic
- Quick data transformation pipelines
Do NOT Use Shell For:
- Complex business logic or data structures
- Performance-critical code
- Scripts requiring extensive error handling
- Anything over ~100 lines or with non-straightforward control flow
- When you need proper data structures beyond arrays
Critical: If your script grows too large (1000+ lines) or complex, consider offering to rewrite it in a proper language (Python, Go, etc.) before it becomes unmaintainable.
Mandatory Foundations
Every bash script must have these elements:
1. Proper Shebang
#!/usr/bin/env bash
Why: Portable across systems where bash may not be at /bin/bash (e.g., macOS, BSD, NixOS).
Alternative: #!/bin/bash if you know the script only runs on Linux and prefer explicit paths.
2. Strict Mode
set -euo pipefail
What each flag does:
-e: Exit immediately if any command fails (non-zero exit)-u: Treat unset variables as errors-o pipefail: Pipe fails if ANY command in pipeline fails (not just the last)
When to add -x: Only for debugging, not in production scripts (makes output noisy).
3. ShellCheck Compliance
Run ShellCheck on EVERY script before committing:
shellcheck script.sh
Fix all warnings. ShellCheck catches:
- Unquoted variables
- Deprecated syntax
- Common bugs and pitfalls
- Portability issues
4. Basic Script Structure
#!/usr/bin/env bash
set -euo pipefail
# Brief description of what this script does
# Simple error reporting
die() {
echo "Error: ${1}" >&2
exit 1
}
# Your code here
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.
- yesterday First seen · 574 lines · 35 tokens per session scan C 0aceed969aa3
shell-scripting is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 7d ago), licensed Apache-2.0. It adds 35 tokens to every session and 3,578 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.
shopify-apps
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions.
yann-lecun-debate
Sub-skill de debates e posições de Yann LeCun. Cobre críticas técnicas detalhadas aos LLMs, rivalidades intelectuais (LeCun vs Hinton, Sutskever, Russell, Yudkowsky, Bostrom), lista completa de rejeições a afirmações mainstream, posição sobre risco existencial de IA, e técnicas de debate ao vivo.
context-guardian
Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.