claude-code-bash-patterns
Claude Code Bash tool patterns with hooks, automation, git workflows.
Sorting a stream of records into a picture
What it does
Status: Production Ready ✅ | Last Verified: 2025-11-18
Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures,…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 3 scripts
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/bash-audit-logger.sh, scripts/dangerous-command-guard.py, scripts/package-manager-enforcer.sh.
Asks for an API key or token
You will need an account with the service it talks to, and your own key. Keep keys in your settings or environment, never in a chat.
How we know
The SKILL.md names API_KEY.
Uses terminal commands
It shows your AI commands to run. In a coding agent that means your terminal; in a chat app it usually can’t.
How we know
The SKILL.md contains shell code blocks.
Deletes backups or system recovery points
Run carelessly — or by an agent working unattended — this can delete work that cannot be recovered.
How we know
templates/dangerous-commands.json line 37: “"example": ":(){ :|:& };:"”. Read 2026-10-05, commit 8837836.
templates/dangerous-commands.json, line 37 ↗Deletes your home folder or the whole drive
Run carelessly — or by an agent working unattended — this can delete work that cannot be recovered.
How we know
scripts/dangerous-command-guard.py line 94 (and 1 more in that file): “(r'rm\s+-rf\s+/', 'Delete root directory (rm -rf /)'),”. Read 2026-10-05, commit 8837836.
scripts/dangerous-command-guard.py, line 94 ↗Reads saved passwords, browser data or wallets
Files like these hold passwords and keys. A skill rarely needs them, and reading them while also sending data out is how secrets get stolen.
How we know
scripts/dangerous-command-guard.py line 139: “(r'>\s*/etc/shadow\b', 'Overwrite /etc/shadow'),”. Read 2026-10-05, commit 8837836.
scripts/dangerous-command-guard.py, line 139 ↗Deletes your home folder or the whole drive
Run carelessly — or by an agent working unattended — this can delete work that cannot be recovered.
How we know
templates/dangerous-commands.json line 7 (and 2 more in that file): “"example": "rm -rf /"”. Read 2026-10-05, commit 8837836.
templates/dangerous-commands.json, line 7 ↗Formats or overwrites a whole disk
Run carelessly — or by an agent working unattended — this can delete work that cannot be recovered.
How we know
templates/dangerous-commands.json line 25 (and 2 more in that file): “"example": "dd if=/dev/zero of=/dev/sda"”. Read 2026-10-05, commit 8837836.
templates/dangerous-commands.json, line 25 ↗Reads saved passwords, browser data or wallets
Files like these hold passwords and keys. A skill rarely needs them, and reading them while also sending data out is how secrets get stolen.
How we know
templates/dangerous-commands.json line 70 (and 2 more in that file): “"pattern": ">\\s*/etc/shadow",”. Read 2026-10-05, commit 8837836.
templates/dangerous-commands.json, line 70 ↗Asks for administrator rights
Some of its commands use sudo or "run as administrator". Those can change anything on your computer.
How we know
Seen in its code. Read 2026-10-05, commit 8837836.
6 smaller things worth knowing
Contains commands that delete or overwrite; Deletes your home folder or the whole drive; Refers to a credentials file (SSH keys, cloud logins, tokens). Usually legitimate — listed so nothing is hidden.
How we know
Contains commands that delete or overwrite — SKILL.md line 251; Contains commands that delete or overwrite — references/git-workflows.md line 353; Contains commands that delete or overwrite — references/hooks-examples.md line 306; Deletes your home folder or the whole drive — references/security-best-practices.md line 61; Contains commands that delete or overwrite — references/security-best-practices.md line 61; Refers to a credentials file (SSH keys, cloud logins, tokens) — references/security-best-practices.md line 196. Read 2026-10-05, commit 8837836.
SKILL.md, line 251 ↗references/git-workflows.md, line 353 ↗references/hooks-examples.md, line 306 ↗references/security-best-practices.md, line 61 ↗references/security-best-practices.md, line 61 ↗references/security-best-practices.md, line 196 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to secondsky/claude-skills: 2026-09-28 (7 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 3 scripts beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from secondsky
All from this publisher →- auto-animate
AutoAnimate (@formkit/auto-animate) zero-config animations for React.
- base-ui-react
MUI Base UI unstyled React components with Floating UI.
- better-auth
Skill for integrating Better Auth - comprehensive TypeScript authentication framework for Cloudflare D1, Next.js, Nuxt, and 15+ frameworks.
- cloudflare-browser-rendering
Cloudflare Browser Rendering with Puppeteer/Playwright.
- cloudflare-cron-triggers
Cloudflare Cron Triggers for scheduled Workers execution.
