18 boosters for "shell" — open source, verified from GitHub, ready to install
Use this agent when documentation in the `architecture/` directory needs to be updated or created for a specific file after implementing a feature, fix, refactor, or behavior change. Launch one instance of this agent per file that needs updating. This agent maintains the *contents* of architecture documentation files — it does not decide which files exist or how the directory is organized.\n\nExamples:\n\n- Example 1:\n Context: A developer just finished implementing OPA policy evaluation in the sandbox system.\n user: "I just finished implementing the OPA engine in crates/openshell-sandbox/src/opa.rs. Update architecture/sandbox.md to reflect the new policy evaluation flow."\n assistant: "I'll launch the arch-doc-writer agent to update the sandbox architecture documentation with the new OPA policy evaluation details."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/sandbox.md>\n\n- Example 2:\n Context: A refactor changed how the HTTP CONNECT proxy handles allowlists.\n user: "The proxy allowlist logic was refactored. Please update architecture/proxy.md."\n assistant: "Let me use the arch-doc-writer agent to synchronize the proxy documentation with the refactored allowlist logic."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/proxy.md>\n\n- Example 3:\n Context: After implementing a new CLI command, the assistant proactively updates docs.\n user: "Add a --rego-policy flag to the CLI."\n assistant: "Here is the implementation of the --rego-policy flag."\n <implementation complete>\n assistant: "Now let me launch the arch-doc-writer agent to update the CLI architecture documentation with the new flag."\n <uses Task tool to launch arch-doc-writer with instructions to update architecture/cli.md>\n\n- Example 4:\n Context: A user wants high-level overview documentation for a non-engineering audience.\n user: "Update architecture/overview.md with a non-engineer-friendly explanation of the sandbox system."\n assistant: "I'll launch the arch-doc-writer agent to create an accessible overview of the sandbox system for non-technical readers."\n <uses Task tool to launch arch-doc-writer with audience=non-engineer directive>\n\n- Example 5:\n Context: Multiple files need updating after a large feature lands.\n user: "I just landed the network namespace isolation feature. Update architecture/sandbox.md and architecture/networking.md."\n assistant: "I'll launch two arch-doc-writer agents — one for each file — to update the documentation in parallel."\n <uses Task tool to launch arch-doc-writer for architecture/sandbox.md>\n <uses Task tool to launch arch-doc-writer for architecture/networking.md>
Master Bash Automated Testing System (Bats) for writing comprehensive unit tests and CI/CD pipeline tests for shell scripts. Essential for developers building production-grade shell utilities and implementing test-driven development practices.
Quickly diagnose which processes are using Shella's port range (47100-47199) to identify port conflicts and running services. Essential for developers debugging local development environments and plugin conflicts.
Nix Development booster provides intelligent assistance for Nix/NixOS development by researching up-to-date information across multiple documentation sources. Developers working with Nix packages, flakes, derivations, and NixOS configurations benefit from accurate, context-aware guidance.
"description": "Smart command safety filter for Claude Code — parses shell pipelines and evaluates per-command safety rules to auto-approve safe commands and block dangerous ones",
"description": "Claude Code skills for SAM — shell alias manager with MCP support", "pluginRoot": "./agent-skills" "source": "./agent-skills",
Expert guidance for the wasmCloud Shell (wash) CLI tool, enabling developers to build, deploy, and manage WebAssembly components and applications efficiently. Essential for teams working with wasmCloud and WebAssembly ecosystems.
Par5 MCP is a parallel execution server that enables running shell commands and AI agents across lists concurrently, ideal for developers automating batch operations and scaling workflows in Claude and other AI environments.
Auralis Commander is a lightweight MCP server that extends Claude Desktop with Windows system access—enabling shell execution, file operations, process management, and system queries. It's ideal for developers and power users who want Claude to interact directly with their Windows environment.
An emergency response toolkit combining shellcode analysis and Linux incident response for security researchers and DevOps teams performing threat investigation and system forensics.
Enforces fish shell as the default shell across Docker, scripts, and development configurations with linting rules and best practices. Benefits teams standardizing on fish shell who want consistent shell environments in Cursor.
This Cursor rules booster enforces fish shell as the default shell by rejecting bash/sh shebangs and promoting fish shell configuration across Docker, environment, and build files. It's useful for teams standardizing on fish shell in their development environments.
Execute PowerShell commands securely within Claude with controlled timeouts and input validation. Useful for developers and system administrators who need to automate Windows tasks or retrieve system information directly from AI conversations.
Enforces a Makefile-only automation policy for a TypeScript/React frontend project, prohibiting shell scripts and standardizing task orchestration for Docker integration. Developers working on the Bacalhau frontend repository benefit from consistent, traceable, and containerization-ready automation practices.
Heuristic scoring (no AI key configured).
Bun Terminal MCP enables AI agents to execute shell commands securely through Claude via Bun's safe $ utility. Developers integrating AI agents with system tasks benefit from this bridge between Claude and terminal operations.
SafeRun provides automatic safety guardrails for AI agents by classifying shell commands as BLOCK, ASK, or ALLOW before execution, preventing dangerous operations like force pushes and recursive deletes. Developers and AI systems that execute shell commands benefit from this protection without needing manual configuration.
A Cursor rules booster that enforces test-driven development practices for shell script writing, helping developers create testable, maintainable scripts with proper separation of concerns. Ideal for shell script developers and teams adopting TDD methodologies.
