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.
git 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/rules/d-padmanabhan/agent-engineering-handbook/140-bash)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/140-bash"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/140-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/rules/d-padmanabhan/agent-engineering-handbook/140-bash"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/140-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 | $0.00000 | $0.00598 |
| Opus 5.5 | $0.00000 | $0.00239 |
| Sonnet 5.5 | $0.00000 | $0.00120 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
140-bash scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash Engineering Gates
This rule owns mandatory policy only. Use the Bash skill (${HANDBOOK_ROOT}/skills/bash-shell-scripting/SKILL.md) for authoring patterns and the automation skill (${HANDBOOK_ROOT}/skills/scripting-automation/SKILL.md) for retries, locks, signals, idempotency, and BATS.
Shell and Error Semantics
- Declare the intended interpreter. Use
#!/usr/bin/env bashonly when Bash features are required; do not claim POSIXshportability while using Bash syntax. - For new non-trivial Bash scripts, use
set -euo pipefailor document a controlled alternative when expected nonzero statuses makeerrexitunsafe. - Handle expected failures explicitly with
if,case,||, or a narrowly scoped error-mode change. Never hide failures with blanket|| true. - Use an
ERRtrap only when it adds actionable context; it is not a substitute for explicit error handling.
Data and Argument Safety
- Quote expansions by default:
"${value}","${array[@]}", and"$@". - Preserve argument boundaries. Never use unquoted
$@,$*, command output, or glob expansion as an argument list. - Use arrays for command arguments. Do not build commands as strings and do not use
evalon untrusted or dynamically assembled data. - Validate allowlisted formats before passing external input to commands, paths, regular expressions, or interpreters.
- Use
printf, notecho -e, for deterministic output.
Files, Processes, and Secrets
- Create temporary files and directories with
mktemp; install a cleanup trap immediately after successful creation. - Quote paths, use
--before user-controlled path operands where supported, and avoid predictable temporary names. - Check command availability before use and fail with a clear remediation message.
- Do not expose secrets through command-line arguments, tracing, logs, process listings, or generated files. Disable
set -xaround sensitive operations. - Bound retries, waits, and background processes; preserve exit status and clean up children on termination.
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.
- 1mo ago First seen · 45 lines · 0 tokens per session scan A 7c18b4da4157
140-bash is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 598 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).