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 G1Joshi/Agent-Skills --skill bashgit clone --depth 1 https://github.com/G1Joshi/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/g1joshi/agent-skills/bash)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/bash"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/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/g1joshi/agent-skills/bash"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/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 | $0.00040 | $0.00968 |
| Opus 5.5 | $0.00016 | $0.00387 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade C, and why
bash scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${TEMP_DIR}" How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash
Bourne Again SHell, the standard shell for Linux and macOS.
When to Use
- Linux System Administration & Automation: Scripting OS maintenance, cron jobs, file backups, and package management.
- CI/CD Pipeline Glue Code: Orchestrating build, test, and container push steps in GitHub Actions and GitLab CI.
- Docker Entrypoint Scripts: Configuring environment variables, secrets, and database wait-for loops during container startup.
- Command-Line Wrappers: Wrapping multi-step CLI commands into simple, repeatable internal developer utilities.
Quick Start
#!/bin/bash
NAME="World"
echo "Hello, $NAME!"
if [ -f "file.txt" ]; then
echo "File exists"
else
echo "File not found"
fi
Core Concepts
Strict Error Handling (set -euo pipefail)
Guarantees script execution aborts on unhandled errors, unset variables, and piped command failures:
#!/usr/bin/env bash
set -euo pipefail
IFS=$'
'
# -e: Exit immediately if a command exits with a non-zero status
# -u: Treat unset variables as an error and exit immediately
# -o pipefail: Pipeline exit status matches the last failing command
Robust Parameter Expansion & Default Values
Safely handles optional and required script variables:
# Provide fallback default if variable unset
TARGET_ENV="${1:-staging}"
# Throw descriptive error if variable is unset or empty
DATABASE_URL="${DATABASE_URL:?Error: DATABASE_URL environment variable is required}"
# Extract filename without extension
filename="archive_2026.tar.gz"
base="${filename%%.*}" # "archive_2026"
Trap Signals for Reliable Cleanup
Ensures temporary files and child processes are cleaned up upon exit or interruption:
TEMP_DIR="$(mktemp -d)"
cleanup() {
echo "Cleaning up temporary files..."
rm -rf "${TEMP_DIR}"
}
trap cleanup EXIT INT TERM
Common Patterns
Safe Script Header with Error and Signal Traps
Problem: Shell scripts fail silently halfway through, leaving orphaned temp files and corrupted state.
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.
- 22d ago Changed · -1 lines 437c4cafd471
- 26d ago Changed · +56 lines · +16 tokens per session scan A → C ce8f571ef543
- 1mo ago First seen · 75 lines · 24 tokens per session scan A 2ac9bf6f3b17
bash is a skill published in the GitHub repository G1Joshi/Agent-Skills (15 stars, last pushed 23d ago), licensed MIT. It adds 40 tokens to every session and 968 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
schedule-recipe
Turn 'run this every Friday at 4pm' into a working, copy-paste schedule on the user's actual runner. Use when asked to schedule a recurring AI task, set up a routine or cron job for a skill, automate a weekly report, or wire a skill into n8n or GitHub Actions. Produces the exact setup for the chosen runner plus the…
meeting-notes-to-tasks
Converts unstructured meeting notes into structured, assigned, time-bounded action items. Never leave a meeting without knowing who does what by when.
proactive-background-watcher
Grants the AI the ability to act proactively using native cron/timer scheduling. The agent can monitor systems, poll APIs, or watch logs in the background and self-trigger without waiting for user prompts.
ci-cd-pipelines
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
interview-me
An interview skill that asks one question at a time to uncover what a user actually needs. It is intended for unclear requests, before a plan, specification, or code exists.