codeagent
Original:🇺🇸 English
Translated
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.
18installs
Sourcecexll/myclaude
Added on
NPX Install
npx skill4agent add cexll/myclaude codeagentTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →Codeagent Wrapper Integration
Overview
Execute codeagent-wrapper commands with pluggable AI backends (Codex, Claude, Gemini). Supports file references via syntax, parallel task execution with backend selection, and configurable security controls.
@When to Use
- Complex code analysis requiring deep understanding
- Large-scale refactoring across multiple files
- Automated code generation with backend selection
Usage
HEREDOC syntax (recommended):
bash
codeagent-wrapper --backend codex - [working_dir] <<'EOF'
<task content here>
EOFWith backend selection:
bash
codeagent-wrapper --backend claude - . <<'EOF'
<task content here>
EOFSimple tasks:
bash
codeagent-wrapper --backend codex "simple task" [working_dir]
codeagent-wrapper --backend gemini "simple task" [working_dir]Backends
| Backend | Command | Description | Best For |
|---|---|---|---|
| codex | | OpenAI Codex (default) | Code analysis, complex development |
| claude | | Anthropic Claude | Simple tasks, documentation, prompts |
| gemini | | Google Gemini | UI/UX prototyping |
Backend Selection Guide
Codex (default):
- Deep code understanding and complex logic implementation
- Large-scale refactoring with precise dependency tracking
- Algorithm optimization and performance tuning
- Example: "Analyze the call graph of @src/core and refactor the module dependency structure"
Claude:
- Quick feature implementation with clear requirements
- Technical documentation, API specs, README generation
- Professional prompt engineering (e.g., product requirements, design specs)
- Example: "Generate a comprehensive README for @package.json with installation, usage, and API docs"
Gemini:
- UI component scaffolding and layout prototyping
- Design system implementation with style consistency
- Interactive element generation with accessibility support
- Example: "Create a responsive dashboard layout with sidebar navigation and data visualization cards"
Backend Switching:
- Start with Codex for analysis, switch to Claude for documentation, then Gemini for UI implementation
- Use per-task backend selection in parallel mode to optimize for each task's strengths
Parameters
- (required): Task description, supports
taskreferences@file - (optional): Working directory (default: current)
working_dir - (required): Select AI backend (codex/claude/gemini)
--backend- Note: Claude backend only adds when explicitly enabled
--dangerously-skip-permissions
- Note: Claude backend only adds
Return Format
Agent response text here...
---
SESSION_ID: 019a7247-ac9d-71f3-89e2-a823dbd8fd14Resume Session
bash
# Resume with codex backend
codeagent-wrapper --backend codex resume <session_id> - <<'EOF'
<follow-up task>
EOF
# Resume with specific backend
codeagent-wrapper --backend claude resume <session_id> - <<'EOF'
<follow-up task>
EOFParallel Execution
Default (summary mode - context-efficient):
bash
codeagent-wrapper --parallel <<'EOF'
---TASK---
id: task1
backend: codex
workdir: /path/to/dir
---CONTENT---
task content
---TASK---
id: task2
dependencies: task1
---CONTENT---
dependent task
EOFFull output mode (for debugging):
bash
codeagent-wrapper --parallel --full-output <<'EOF'
...
EOFOutput Modes:
- Summary (default): Structured report with changes, output, verification, and review summary.
- Full (): Complete task messages. Use only when debugging specific failures.
--full-output
With per-task backend:
bash
codeagent-wrapper --parallel <<'EOF'
---TASK---
id: task1
backend: codex
workdir: /path/to/dir
---CONTENT---
analyze code structure
---TASK---
id: task2
backend: claude
dependencies: task1
---CONTENT---
design architecture based on analysis
---TASK---
id: task3
backend: gemini
dependencies: task2
---CONTENT---
generate implementation code
EOFConcurrency Control:
Set to limit concurrent tasks (default: unlimited).
CODEAGENT_MAX_PARALLEL_WORKERSEnvironment Variables
- : Override timeout in milliseconds (default: 7200000 = 2 hours)
CODEX_TIMEOUT - : Control Claude CLI permission checks
CODEAGENT_SKIP_PERMISSIONS- For Claude backend: Set to /
trueto add1(default: disabled)--dangerously-skip-permissions - For Codex/Gemini backends: Currently has no effect
- For Claude backend: Set to
- : Limit concurrent tasks in parallel mode (default: unlimited, recommended: 8)
CODEAGENT_MAX_PARALLEL_WORKERS
Invocation Pattern
Single Task:
Bash tool parameters:
- command: codeagent-wrapper --backend <backend> - [working_dir] <<'EOF'
<task content>
EOF
- timeout: 7200000
- description: <brief description>
Note: --backend is required (codex/claude/gemini)Parallel Tasks:
Bash tool parameters:
- command: codeagent-wrapper --parallel --backend <backend> <<'EOF'
---TASK---
id: task_id
backend: <backend> # Optional, overrides global
workdir: /path
dependencies: dep1, dep2
---CONTENT---
task content
EOF
- timeout: 7200000
- description: <brief description>
Note: Global --backend is required; per-task backend is optionalCritical Rules
NEVER kill codeagent processes. Long-running tasks are normal. Instead:
-
Check task status via log file:bash
# View real-time output tail -f /tmp/claude/<workdir>/tasks/<task_id>.output # Check if task is still running cat /tmp/claude/<workdir>/tasks/<task_id>.output | tail -50 -
Wait with timeout:bash
# Use TaskOutput tool with block=true and timeout TaskOutput(task_id="<id>", block=true, timeout=300000) -
Check process without killing:bash
ps aux | grep codeagent-wrapper | grep -v grep
Why: codeagent tasks often take 2-10 minutes. Killing them wastes API costs and loses progress.
Security Best Practices
- Claude Backend: Permission checks enabled by default
- To skip checks: set or pass
CODEAGENT_SKIP_PERMISSIONS=true--skip-permissions
- To skip checks: set
- Concurrency Limits: Set in production to prevent resource exhaustion
CODEAGENT_MAX_PARALLEL_WORKERS - Automation Context: This wrapper is designed for AI-driven automation where permission prompts would block execution
Recent Updates
- Multi-backend support for all modes (workdir, resume, parallel)
- Security controls with configurable permission checks
- Concurrency limits with worker pool and fail-fast cancellation