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/vikasudasi/skill-vault/bash-scripting-safenpx skills add vikasudasi/skill-vault --skill bash-scripting-safegit clone --depth 1 https://github.com/vikasudasi/skill-vaultWhat 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 | $0.00038 | $0.01121 |
| Opus 5 | $0.00019 | $0.00561 |
| Sonnet 5 | $0.00008 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
bash-scripting-safe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Bash Scripting
Use when writing a shell script that must not corrupt files, delete the wrong thing, or silently fail. Bash is powerful precisely because it's dangerous — the discipline below is what makes it safe.
Always start with these three lines
#!/usr/bin/env bash
set -euo pipefail
-e— exit on first failing command (no silent mid-script failure).-u— error on unset variable (catches typos like$filevs$files).-o pipefail— a failing command anywhere in a pipeline fails the pipeline.
Add IFS=$'\n\t' when you parse output: it changes Bash's default word-splitting
(space, tab, newline) to just newline + tab, so filenames containing spaces no
longer get split into multiple arguments.
Quote everything (word splitting is the #1 data-loss path)
dir="$1" # quote expansions
for f in "$dir"/*.txt; do # quotes + glob
cp "$f" "$dest/"
done
Unquoted $var undergoes word splitting (splits on spaces) and globbing
(* and ? expand). The classic disaster:
# WRONG — if "$file" contains a space, rm deletes multiple files; glob expansion is worse
rm $file
# RIGHT
rm -- "$file"
A variable is only safe unquoted when you intend splitting/globbing. Prefer
"$@"-style quoting everywhere else.
Redirects and atomic file writes
- Use a temp file +
mvfor atomic writes; never>straight onto a file you also read later in the same script (it truncates the input mid-run):
tmp="$(mktemp)"
trap 'rm -f "$tmp"' EXIT # clean up scratch even on error
grep foo input.txt > "$tmp"
mv "$tmp" output.txt # atomic swap
mktempfor scratch files (safer than hard-coded/tmp/namewhich can collide or be a symlink).trap ... EXITguarantees cleanup on failure.- Beware
set -e+ empty globs:"$dir"/*.txtwith no matches stays a literal*.txtstring — check withshopt -s nullglobor test existence.
Error handling
if ! command -v jq >/dev/null 2>&1; then
echo "jq is required" >&2
exit 1
fi
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 123 lines · 38 tokens per session scan A 4c194271d342
bash-scripting-safe is a skill published in the GitHub repository vikasudasi/skill-vault (0 stars, last pushed 17d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,121 once invoked, about $0.0002 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.
Other skills, from other repositories
shell-scripting
Use this skill when writing bash or zsh scripts, parsing arguments, handling errors, or automating CLI workflows. Triggers on bash scripting, shell scripts, argument parsing, process substitution, here documents, signal trapping, exit codes, and any task requiring portable shell script development.
shell-scripting
Skill "shell-scripting" from chaterm/terminal-skills, covering shell 脚本编写, 概述, 基础语法, 脚本结构 and 脚本描述.
bash-scripting
Use when writing or hardening a shell script that must survive another machine — a CI step, install script, cron job, git hook, devcontainer entrypoint: strict-mode leaks, quoting/word-splitting, arrays, trap cleanup, bash-vs-POSIX portability, ShellCheck findings. NOT CI workflow structure, runners, caching or matrix…
bash-defensive-patterns
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
shell-bash
Shell scripting and Bash programming patterns.
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…