safe-bash

safe-bash is a skill for Claude Code, Codex from baphuongna/pi-crew. It costs 9 tokens per session (2,210 once invoked), scanned D, original, MIT.

A safe shell-command workflow for coding agents. It distinguishes commands that only inspect files from commands that change or delete data, with guidance for Unix and Windows.

In plain words
What is it for?
It helps classify commands, request confirmation before changes, handle platform-specific paths, and choose safer ways to inspect or modify a project.
Why use it?
It reduces the risk of accidentally changing files, rewriting Git history, publishing packages, or running unsafe commands.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/baphuongna/pi-crew/safe-bash
Any agent
npx skills add baphuongna/pi-crew --skill safe-bash
Clone the repo
git clone --depth 1 https://github.com/baphuongna/pi-crew

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for safe-bash

README.md
[![agentmods](https://agentmods.dev/badge/skills/baphuongna/pi-crew/safe-bash.svg)](https://agentmods.dev/skills/baphuongna/pi-crew/safe-bash)
Your own site
<a href="https://agentmods.dev/skills/baphuongna/pi-crew/safe-bash"><img src="https://agentmods.dev/badge/skills/baphuongna/pi-crew/safe-bash.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,210 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.02210
Opus 5 $0.00005 $0.01105
Sonnet 5 $0.00002 $0.00442
Haiku 4.5 $0.00001 $0.00221

Measured 5d ago against content hash 86cbfd165587, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade D, and why

safe-bash scanned grade D with 3 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

### Avoiding sudo prompts in scripts

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf <path> # DESTRUCTIVE

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { spawn } from "child_process";
skills/safe-bash/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

safe-bash

Use this skill whenever a task may execute shell commands. This skill covers cross-platform shell safety, destructive action confirmation, and Windows-specific patterns.

Classification

Every shell command is either read-only or mutating. Always report which it is.

Read-only commands (safe)

pwd              # print working directory
ls -la           # list files
find . -name "*.ts" | head -20        # search without writing
rg "pattern" --type ts | head -20     # ripgrep without write
git status       # inspect state
git log --oneline -5  # recent commits
git diff --staged    # staged changes
npm view <pkg>   # query registry (no install)
npx tsc --noEmit  # typecheck (no write)
node -e "console.log(process.version)"  # inspect version

Mutating commands (require confirmation)

npm install      # changes node_modules
git commit       # creates new commit
git push         # publishes to remote
rm -rf <path>    # DESTRUCTIVE
git reset --hard # rewrites history
npm publish      # publishes to registry

Cross-Platform Considerations

Windows vs Unix paths

// ❌ Never hardcode paths with forward slashes on Windows
const path = "D:/project/src/file.ts";

// ✅ Use path.join() or Node's path module
import * as path from "path";
const filePath = path.join(cwd, "src", "file.ts");

// ✅ Or use forward slashes that work on both
const filePath = "src/file.ts"; // relative paths work on both

argv vs cmd /c

// ✅ Preferred on Windows: argv-based execution (no shell)
import { spawn } from "child_process";
spawn("node", ["--version"], { stdio: "pipe" });

// ✅ If shell needed: use cmd /c explicitly
spawn("cmd", ["/c", "dir /b"], { stdio: "pipe" });

// ❌ Don't use cmd /c with complex commands as single string
spawn("cmd", ["/c", "node --version && npm test"], { stdio: "pipe" });

Package manager detection

// Detect npm vs pnpm vs yarn
function detectPackageManager(cwd: string): "npm" | "pnpm" | "yarn" | "unknown" {
  if (fs.existsSync(path.join(cwd, "pnpm-lock.yaml"))) return "pnpm";
  if (fs.existsSync(path.join(cwd, "yarn.lock"))) return "yarn";
  return "npm";
}

Read the full file on GitHub · 323 lines

Changes

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.

  1. 5d ago First seen · 323 lines · 9 tokens per session scan D 86cbfd165587

Subscribe to this mod's changes

safe-bash is a skill published in the GitHub repository baphuongna/pi-crew (51 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 2,210 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens