read-task — community read-task, dual-agent, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for collaborative AI Agents like Claude Code and Codex CLI that require seamless task delegation and execution in a tmux session Dual-agent development environment pairing Claude Code with Codex CLI in a collaborative tmux session

antorsae antorsae
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The read-task skill by antorsae is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for collaborative AI Agents like Claude Code and Codex CLI that require seamless task delegation and execution in a tmux session

Core Value

Empowers agents to read and execute tasks delegated from Claude Code, utilizing the `.agent-collab` directory for collaborative workflow management and facilitating commands outside the project root with bash scripting and directory resolution

Capabilities Granted for read-task

Executing tasks delegated from Claude Code
Managing collaborative workflows in a tmux session
Resolving directory paths for seamless command execution

! Prerequisites & Limits

  • Requires bash scripting capabilities
  • Dependent on `.agent-collab` directory resolution
  • Limited to collaborative environments with Claude Code and Codex CLI
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

read-task

Install read-task, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Read Task Skill

Read and execute a task delegated from Claude Code.

Steps

Before any file operations, resolve the .agent-collab directory so commands work outside the project root:

bash
1AGENT_COLLAB_DIR="${AGENT_COLLAB_DIR:-}" 2if [ -n "$AGENT_COLLAB_DIR" ]; then 3 if [ -d "$AGENT_COLLAB_DIR/.agent-collab" ]; then 4 AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab" 5 elif [ ! -d "$AGENT_COLLAB_DIR" ]; then 6 AGENT_COLLAB_DIR="" 7 fi 8fi 9 10if [ -z "$AGENT_COLLAB_DIR" ]; then 11 AGENT_COLLAB_DIR="$(pwd)" 12 while [ "$AGENT_COLLAB_DIR" != "/" ] && [ ! -d "$AGENT_COLLAB_DIR/.agent-collab" ]; do 13 AGENT_COLLAB_DIR="$(dirname "$AGENT_COLLAB_DIR")" 14 done 15 AGENT_COLLAB_DIR="$AGENT_COLLAB_DIR/.agent-collab" 16fi

If $AGENT_COLLAB_DIR does not exist, stop and ask for the project root.

1. Update Status

Write working to $AGENT_COLLAB_DIR/status

2. Read the Task

Read $AGENT_COLLAB_DIR/requests/task.md and parse:

  • Task Type: CODE_REVIEW, IMPLEMENT, or PLAN_REVIEW
  • All requirements and context

3. Read Shared Context

Also read $AGENT_COLLAB_DIR/context/shared.md for project context.

4. Execute Based on Task Type

CODE_REVIEW

Perform thorough code review:

  • Analyze code line by line
  • Look for bugs, logic errors, edge cases
  • Check for security vulnerabilities
  • Identify performance problems
  • Check error handling
  • Suggest concrete improvements with code examples

Be thorough - take your time.

IMPLEMENT

Implement the requested feature:

  • Follow all requirements exactly
  • Match existing code patterns
  • Write clean, well-structured code
  • Handle edge cases and errors
  • Write code to specified target files

Take time for high-quality implementation.

PLAN_REVIEW

Critically analyze the plan:

  • Evaluate overall approach
  • Identify failure modes
  • Consider scalability/maintainability
  • Suggest alternatives if applicable
  • Point out missing considerations
  • Assess risks
  • Provide concrete recommendations

5. Write Response

Write complete response to $AGENT_COLLAB_DIR/responses/response.md:

markdown
1# Codex Response 2 3## Task Type 4[Task type handled] 5 6## Completed At 7[Timestamp] 8 9## Summary 10[Brief summary] 11 12## Detailed Findings/Output 13 14[For CODE_REVIEW:] 15### Critical Issues 16[List with severity] 17 18### Security Concerns 19[Security issues] 20 21### Suggestions 22[Improvements with examples] 23 24--- 25 26[For IMPLEMENT:] 27### Implementation Overview 28[What was implemented] 29 30### Files Created/Modified 31[List of files] 32 33### Integration Notes 34[How to integrate] 35 36--- 37 38[For PLAN_REVIEW:] 39### Overall Assessment 40[Is plan sound?] 41 42### Concerns 43[Issues identified] 44 45### Recommendations 46[Specific suggestions]

6. Update Status

Write done to $AGENT_COLLAB_DIR/status

7. Notify

Tell user response is ready and Claude can read it with /codex-read.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is read-task?

Ideal for collaborative AI Agents like Claude Code and Codex CLI that require seamless task delegation and execution in a tmux session Dual-agent development environment pairing Claude Code with Codex CLI in a collaborative tmux session

How do I install read-task?

Run the command: npx killer-skills add antorsae/dual-agent/read-task. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for read-task?

Key use cases include: Executing tasks delegated from Claude Code, Managing collaborative workflows in a tmux session, Resolving directory paths for seamless command execution.

Which IDEs are compatible with read-task?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for read-task?

Requires bash scripting capabilities. Dependent on `.agent-collab` directory resolution. Limited to collaborative environments with Claude Code and Codex CLI.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add antorsae/dual-agent/read-task. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use read-task immediately in the current project.

Related Skills

Looking for an alternative to read-task or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI