Agent skill
Fork Bash Skill
Execute agentic coding tools directly via bash commands with output capture. Use this when the user requests to run AI agents (Gemini, Claude Code, etc.) and get their results directly.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/fork-bash-skill-mattnigh-skills-collection
SKILL.md
Purpose
Execute agentic coding tools directly via bash commands and capture their output in real-time. This is a simpler and more reliable alternative to fork-terminal for one-off tasks.
Follow the Instructions, execute the Workflow, based on the Cookbook.
Variables
ENABLE_GEMINI_CLI: true ENABLE_CLAUDE_CODE: true ENABLE_CODEX_CLI: true AGENTIC_CODING_TOOLS: gemini, claude-code, codex
Instructions
- Based on the user's request, follow the
Cookbookto determine which tool to use. - Execute the command directly using bash and capture stdout/stderr
- Return the output to the user immediately
Workflow
- Understand the user's request
- Follow the
Cookbookto determine which tool to use - Construct the appropriate bash command
- Execute using the Bash tool with appropriate timeout
- Return results to the user
Cookbook
Gemini CLI
- IF: The user requests Gemini to execute a task AND
ENABLE_GEMINI_CLIis true - THEN: Read and execute:
.claude/skills/fork-bash/cookbook/gemini-cli.md - EXAMPLES:
- "Use Gemini to scrape the latest news from CNN"
- "Ask Gemini to analyze this webpage"
- "Run Gemini with yolo mode to get information about X"
Claude Code
- IF: The user requests Claude Code agent AND
ENABLE_CLAUDE_CODEis true - THEN: Read and execute:
.claude/skills/fork-bash/cookbook/claude-code.md - EXAMPLES:
- "Use Claude Code to refactor this file"
- "Ask Claude Code to analyze the codebase"
Codex CLI
- IF: The user requests Codex AND
ENABLE_CODEX_CLIis true - THEN: Read and execute:
.claude/skills/fork-bash/cookbook/codex-cli.md - EXAMPLES:
- "Use Codex to generate code for X"
- "Ask Codex to explain this function"
Notes
- This skill executes commands synchronously and captures output
- Use appropriate timeouts based on task complexity
- Always use YOLO mode (-y flag) for automated execution
- Output is captured directly from stdout/stderr
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?