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 joao-aires/agent-skills-public --skill bash-engineeringgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/bash-engineering)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/bash-engineering"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/bash-engineering/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/joao-aires/agent-skills-public/bash-engineering"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/bash-engineering.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 | $0.00043 | $0.00845 |
| Opus 5.5 | $0.00017 | $0.00338 |
| Sonnet 5.5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
bash-engineering 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 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash engineering
Use Bash to orchestrate commands when the inputs, outputs and failure behavior remain easy to follow. Design the script as an interface: establish what its caller supplies, what stdout means, what diagnostics go to stderr, and which exit status signals failure. Preserve those contracts when changing a script used by other commands or CI.
Follow critical commands through failure as carefully as through success. Decide whether the next action is still valid after a command fails and preserve that result through logging and cleanup. Shell options support that design but do not replace explicit reasoning about pipelines, substitutions and expected nonzero statuses. Move substantial data modeling, API coordination or complex state management to a structured language when that makes maintenance simpler.
Modes and discovery
- Interactive/setup: inspect the required shell version, OS/tools, CLI inputs and operational effects; explain design choices and implement the selected contract.
- Feature/maintenance: preserve documented interfaces and callers, correct failure/quoting behavior, and update examples/tests with changes.
- Recurring review: audit changed entrypoints and inline CI shell, identify reproducible defects, prepare bounded patches and fixture tests, and retain stable findings. Do not run remote mutations merely to test scripts.
Discover actual callers, local/CI environments, GNU/BSD requirements, secrets, stdout consumers and mutation scope before editing. Consult the Bash guide for deeper implementation details; for CI integration also read action boundaries.
Define the command interface
Establish arguments/options, defaults, required tools, stdout/stderr, exit codes, no-op behavior and side effects. Unknown, missing and invalid options must fail clearly; --help must work without credentials. If another program consumes stdout, reserve it for the documented result and send useful sanitized diagnostics elsewhere. Keep CI grouping/outputs at the wrapper boundary so the underlying tool retains a normal CLI contract.
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.
- yesterday Changed · +13 lines 4363cc026e25
- 7d ago First seen · 41 lines · 43 tokens per session scan A 96193506c22a
bash-engineering is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 845 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…