shell_command

shell_command is a skill for Claude Code, Codex from aiguicai/MCP-Gateway. It costs 150 tokens per session (4,817 once invoked), scanned A, original, MIT.

A controlled way to run non-interactive terminal commands inside approved project folders.

In plain words
What is it for?
Use it for project exploration, text searches, Git checks, development servers, tests, builds, and project scripts.
Why use it?
It helps agents inspect files, search code, run tests, builds, and formatters while keeping the working directory and command execution constrained.

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/aiguicai/mcp-gateway/shell_command
Any agent
npx skills add aiguicai/MCP-Gateway --skill shell_command
Clone the repo
git clone --depth 1 https://github.com/aiguicai/MCP-Gateway

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 shell_command

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/shell_command.svg)](https://agentmods.dev/skills/aiguicai/mcp-gateway/shell_command)
Your own site
<a href="https://agentmods.dev/skills/aiguicai/mcp-gateway/shell_command"><img src="https://agentmods.dev/badge/skills/aiguicai/mcp-gateway/shell_command.svg" alt="Measured on agentmods" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,817 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00150 $0.04817
Opus 5 $0.00075 $0.02409
Sonnet 5 $0.00030 $0.00963
Haiku 4.5 $0.00015 $0.00482

Measured 3d ago against content hash 203ecc2f540f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shell_command 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 3d 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.

mcp-gateway/crates/gateway-http/builtin-skills/shell_command/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell Command

Use this bundled skill when the task is best handled by a terminal command: listing files, searching text, reading files, checking Git state, running builds/tests/formatters, starting a local dev server, or executing a project script.

This skill is intentionally a small terminal orchestration layer. It follows the same practical pattern used by coding agents such as Codex: keep commands non-interactive, keep the working directory explicit, prefer fast search/read tools, stream output back to the model, and let policy decide whether sensitive commands are allowed, denied, or require user confirmation.

Global Search And Discovery Priority

  • Treat rg as the default first tool for all project exploration and narrowing work, including project structure, file discovery, code navigation, symbol lookup, call-site discovery, config lookup, workflow tracing, tests, routes, error messages, broad inventories, and "where is this implemented?" questions.
  • Use rg to locate candidate files and line numbers before reading file contents. Do not read many whole files to discover where something lives.
  • Use rg --files first for project structure, file discovery, broad inventories, and file counts.
  • Use rg -n "pattern" path first for text/code search, workflow tracing, symbol references, config keys, routes, CLI commands, and error strings.
  • Use rg -n -m 20 "pattern" path when the initial result could be large.
  • Use rg --files | rg "name-or-extension" for fast filename narrowing.
  • Use git ls-files for "tracked files only" counts or inventories.
  • Use Get-ChildItem only for simple, shallow Windows directory listings, for example Get-ChildItem -Name or Get-ChildItem -Name -Filter *.rs.
  • Do not use Get-ChildItem -Recurse, find . -type f, dir /s, ls -R, or du for repository-wide discovery, search, inventories, or counts unless the command includes explicit exclusions and rg is unavailable.
  • Never treat dependency folders, VCS metadata, generated outputs, virtual environments, or caches as meaningful project files in broad counts.

Read the full file on GitHub · 244 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. 3d ago First seen · 244 lines · 150 tokens per session scan A 203ecc2f540f

Subscribe to this mod's changes

shell_command is a skill published in the GitHub repository aiguicai/MCP-Gateway (153 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session and 4,817 once invoked, about $0.0007 per session on Opus 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 2026-08-30.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens