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 d-padmanabhan/agent-engineering-handbook --skill scripting-automationgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/scripting-automation)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/scripting-automation"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/scripting-automation/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/d-padmanabhan/agent-engineering-handbook/scripting-automation"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/scripting-automation.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 | $0.00073 | $0.03752 |
| Opus 5 | $0.00036 | $0.01876 |
| Sonnet 5 | $0.00015 | $0.00750 |
| Haiku 4.5 | $0.00007 | $0.00375 |
Grade C, and why
scripting-automation scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TEST_DIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use for: Diagnostics, cleanup operations, commands where failure is expected (grep, curl with retries). How it starts
The opening of the file, as written. The whole thing — 572 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scripting & Automation
Use the Bash skill (${HANDBOOK_ROOT}/skills/bash-shell-scripting/SKILL.md) for baseline shell authoring. This skill owns automation-specific retries, locks, signals, idempotency, deployment workflows, and BATS patterns.
Guiding Principles
- "Fail fast, fail clearly" - Use strict mode, validate early, provide clear error messages
- "Quotes are your friend" - Always quote variables unless you explicitly want word splitting
- "Explicit over implicit" - Use
local,readonly, clear function names, document assumptions - "Security by default" - Sanitize inputs, use
mktemp, avoideval, validate file paths - "Composition over complexity" - Small functions, clear separation of concerns, reusable patterns
- "Observability is essential" - Structured logging, proper exit codes, error context
- "Test what you write" - Use shellcheck, test on multiple platforms, write BATS tests
- "Format consistently" - Must pass
shfmt -i 2 -ci -sr -bn(2-space indentation; prefer ~100-character lines)
Quick Reference
# Safety modes
set -euo pipefail # Strict mode (fail-fast)
set -uo pipefail # Controlled mode (explicit error handling)
set -Euo pipefail # Strict + ERR trap propagation to functions
# Common patterns
command -v cmd >/dev/null # Check if command exists (portable)
trap 'cleanup' EXIT # Always cleanup
flock -n 200 || exit 1 # Prevent concurrent runs
readonly VAR="value" # Immutable constant
local var="value" # Function-local variable
shfmt -w -i 2 -ci -sr -bn . # Format with Google-style 2-space indentation
Standard Header + Prelude
Use this for new automation scripts. It documents purpose and usage, keeps debug tracing available but commented, creates a timestamped logfile named after the script, and uses a safe logging helper instead of raw echo.
#!/usr/bin/env bash
#
# Script Name : <script_name>.sh
#
# Purpose : <One or two sentences explaining what the script does.
# Wrap continuation lines under the value column.>
#
# Dependencies : <List required commands, or "None">
#
# Script Usage : ./<script_name>.sh [options] <arguments>
#
# <Examples and argument notes.>
#
##----------------------------------------------------------------------------------------##
# Turn debug on or off
# set -x
##----------------------------------------------------------------------------------------##
set -euo pipefail
readonly DTTM="$(date -u +"%Y%m%d_%H%M%S")"
readonly SCRIPT_NAME="$(basename "${0}" .sh)"
readonly LOGFILE="${SCRIPT_NAME}_${DTTM}.log"
logmsg() {
local timestamp
timestamp="$(date -u +"%Y-%m-%dT%H:%M:%SZ")"
printf "%s: %s\n" "${timestamp}" "$*" | tee -a "${LOGFILE}" >&2
}
die() {
logmsg "ERROR: $*"
exit 1
}
debug() {
[[ "${DEBUG:-0}" == "1" ]] && logmsg "DEBUG: $*"
}
require_command() {
local command_name="$1"
command -v "${command_name}" >/dev/null 2>&1 || die "Missing command: ${command_name}"
}
What ships with it
1 file 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.
- 8d ago First seen · 572 lines · 73 tokens per session scan C 5f375c28b66e
scripting-automation is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 3,752 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…
migrate-vstest-to-mtp
Use this skill before answering, planning, or editing whenever .NET tests or CI are switching from VSTest to Microsoft.Testing.Platform (MTP), or an MTP migration behaves differently. Triggers include "switch from VSTest"; MSTest/NUnit/xUnit MTP enablement; OutputType=Exe only for test projects in…
playwright-ci
Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
ci-maintenance-workflow
CI and GitHub Actions maintenance workflows — fix a failing test from a CI URL, fix a failing smoke test, add @pytest.mark.slow markers to slow tests, or review a PR against agent-checkable standards. Use when user asks to fix a failing test, fix a smoke test, mark slow tests, or review a PR. Trigger when the user…
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.