command-execution-principles

command-execution-principles is a skill for Claude Code, Gemini CLI from irahardianto/rugged-gemini. It costs 34 tokens per session (957 once invoked), scanned B, original, MIT.

A set of rules for running operating-system commands safely from software or coding agents. It covers input validation, argument handling, timeouts, error output, permissions, portability, and non-interactive execution.

In plain words
What is it for?
Use it when spawning processes, running shell commands, handling command output and exit codes, setting time limits, or making command execution work across Windows, macOS, and Linux.
Why use it?
It reduces risks such as command injection, accidental privileged actions, stuck prompts, ignored failures, and code that only works on one operating system.

Skill for Claude CodeGemini CLI

Written for Claude Code and Gemini CLI: user-invocable in frontmatter, but also installed under .gemini/. Also seen: mentions Gemini CLI.

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/irahardianto/rugged-gemini/command-execution-principles
Any agent
npx skills add irahardianto/rugged-gemini --skill command-execution-principles
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Claude Code, Gemini CLI.

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 command-execution-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/irahardianto/rugged-gemini/command-execution-principles.svg)](https://agentmods.dev/skills/irahardianto/rugged-gemini/command-execution-principles)
Your own site
<a href="https://agentmods.dev/skills/irahardianto/rugged-gemini/command-execution-principles"><img src="https://agentmods.dev/badge/skills/irahardianto/rugged-gemini/command-execution-principles.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00034 $0.00957
Opus 5 $0.00017 $0.00478
Sonnet 5 $0.00007 $0.00191
Haiku 4.5 $0.00003 $0.00096

Measured 5d ago against content hash edde0778160d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

command-execution-principles scanned grade B with 1 finding 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.

- Never run as root/admin without explicit human approval. Elevated perms required → STOP and request auth.
.gemini/skills/command-execution-principles/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command Execution Principles

Security

  • exec(userInput), shell("rm " + userFile)
  • ✅ Argument lists (no shell string concat), validate/sanitize all args
  • Never run as root/admin without explicit human approval. Elevated perms required → STOP and request auth.
  • Least-privilege service accounts

Portability

  • Use language stdlib over shell commands (file I/O APIs instead of cat/cp/mv)
  • Test on all target OS (path joining functions, not / concatenation)

Error Handling

  • Check exit codes (non-zero = failure)
  • Capture + log stderr
  • Set timeouts for long-running
  • Handle "command not found" gracefully

Non-Interactive Mode (MANDATORY for AI Agents)

AI agents CANNOT interact with interactive prompts. All commands MUST run non-interactively. A stuck prompt = a stuck agent = wasted time.

Environment Variables (set before ANY npm/yarn/pnpm command)
export CI=true               # Signals non-interactive environment to most tools
export npm_config_yes=true   # npm: auto-accept all prompts
export YARN_ENABLE_IMMUTABLE_INSTALLS=false  # Yarn: don't fail on lockfile changes
npm / npx
# ✅ CORRECT — always use --yes for npx
npx -y create-vite@latest ./my-app -- --template vue-ts
npx -y create-next-app@latest ./my-app --ts --eslint --app --use-npm

# ✅ CORRECT — npm install (CI=true suppresses prompts)
CI=true npm install
CI=true npm ci              # Preferred for reproducible installs

# ❌ WRONG — interactive, WILL HANG
npx create-vite@latest my-app
npm init
npm create vite
Scaffolding Tools (create-vite, create-next-app, etc.)

Every scaffolding tool has a non-interactive mode. You MUST find and use it.

  1. Run --help first to discover non-interactive flags before scaffolding
  2. Always pass all required options (template, name, etc.) as CLI flags
  3. Common patterns:
    • create-vite: --template <template> (must specify template to skip prompt)
    • create-next-app: --ts --eslint --app --use-npm (pass all choices as flags)
    • create-react-app: pass project name as argument
    • npm init <initializer>: use npm create <initializer> -- <flags> with --yes or template flags
  4. If a tool still prompts, pipe yes | as last resort: yes | npx -y create-tool ...

Read the full file on GitHub · 105 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 · 105 lines · 34 tokens per session scan B edde0778160d

Subscribe to this mod's changes

command-execution-principles is a skill published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 957 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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-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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens