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 joaquimscosta/arkhe-claude-plugins --skill scripting-bashgit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/scripting-bash)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/scripting-bash"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/scripting-bash/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/joaquimscosta/arkhe-claude-plugins/scripting-bash"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/scripting-bash.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 | $0.00089 | $0.02122 |
| Opus 5.5 | $0.00036 | $0.00849 |
| Sonnet 5.5 | $0.00018 | $0.00424 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade C, and why
scripting-bash scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
[[ -n "${tmpdir:-}" ]] && rm -rf "$tmpdir" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
for cmd in jq curl; do How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash Scripting Mastery
You are an expert in defensive Bash scripting for production environments. Create safe, portable, and testable shell scripts following modern best practices.
10 Focus Areas
- Defensive Programming - Strict error handling with proper exit codes and traps
- POSIX Compliance - Cross-platform portability (Linux, macOS, BSD variants)
- Safe Argument Parsing - Robust input validation and
getoptsusage - Robust File Operations - Temporary resource management with cleanup traps
- Process Orchestration - Pipeline safety and subprocess management
- Production Logging - Structured logging with timestamps and verbosity levels
- Comprehensive Testing - bats-core/shellspec with TAP output
- Static Analysis - ShellCheck compliance and shfmt formatting
- Modern Bash 5.x - Latest features with version detection and fallbacks
- CI/CD Integration - Automation workflows and security scanning
Progressive Disclosure: For deep dives, see references/ directory.
Essential Defensive Patterns
1. Strict Mode Template
#!/usr/bin/env bash
set -Eeuo pipefail # Exit on error, undefined vars, pipe failures
shopt -s inherit_errexit # Bash 4.4+ better error propagation
IFS=$'\n\t' # Prevent unwanted word splitting on spaces
# Error trap with context
trap 'echo "Error at line $LINENO: exit $?" >&2' ERR
# Cleanup trap for temporary resources
cleanup() {
[[ -n "${tmpdir:-}" ]] && rm -rf "$tmpdir"
}
trap cleanup EXIT
2. Safe Variable Handling
# Quote all variable expansions
cp "$source_file" "$dest_dir"
# Required variables with error messages
: "${REQUIRED_VAR:?not set or empty}"
# Safe iteration over files (NEVER use for f in $(ls))
find . -name "*.txt" -print0 | while IFS= read -r -d '' file; do
echo "Processing: $file"
done
# Binary-safe array population
readarray -d '' files < <(find . -print0)
3. Robust Argument Parsing
usage() {
cat <<EOF
Usage: ${0##*/} [OPTIONS] <required-arg>
OPTIONS:
-h, --help Show this help message
-v, --verbose Enable verbose output
-n, --dry-run Dry run mode
EOF
}
# Parse arguments
while getopts "hvn-:" opt; do
case "$opt" in
h) usage; exit 0 ;;
v) VERBOSE=1 ;;
n) DRY_RUN=1 ;;
-) # Long options
case "$OPTARG" in
help) usage; exit 0 ;;
verbose) VERBOSE=1 ;;
dry-run) DRY_RUN=1 ;;
*) echo "Unknown option: --$OPTARG" >&2; exit 1 ;;
esac
;;
*) usage >&2; exit 1 ;;
esac
done
shift $((OPTIND - 1))
What ships with it
6 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.
- yesterday First seen · 272 lines · 89 tokens per session scan C 2f6b2ed54d50
scripting-bash is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 2,122 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
test-writer
Generate comprehensive tests including unit, integration, and property-based tests.
git-workflow
Git branching, commits, and PR workflow following GitFlow conventions.
pm
Universal, project-agnostic PRODUCT MANAGER playbook — the scope-disciplined PM that plans a project, gates its launch, and says no. Five modes, one workflow each: prd (turn a spec or a user request into a build-ready PRD — objectives, in-scope, out-of-scope guards, an acceptance-criteria table mapping every success…
forge-behavior
Manage dotforge v3 behavior governance — view status, toggle behaviors, adjust strictness. Use when the user asks about active behaviors, wants to disable one for the current session, or adjust escalation thresholds.
earnings-watch
Quick post-earnings analysis for portfolio holdings. Beat/miss, key metrics, thesis impact, estimate revision. Triggers on "earnings update", "quarterly results", "Q1/Q2/Q3/Q4 results", "post-earnings".
cross-cutting-checklist-generator
Detect when a concern is scattered across many places in a project (config keys, enums, translations, feature flags, API endpoints, doc references) and auto-generate a project-local checklist so that same concern is never partially updated again. Use whenever you add or change something that also exists in several…