← Back to Skills Marketplace
Claude Delegate
by
splicer scorn
· GitHub ↗
· v1.0.0
· MIT-0
433
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install claude-delegate
Description
Delegate various coding tasks to Claude Code. Use this skill when you need assistance with code generation, bug fixing, feature implementation, code review,...
README (SKILL.md)
Claude Delegate
Use this skill to delegate coding tasks to Claude Code. It simplifies the process by providing the correct command structure for non-interactive execution.
Usage
To delegate a task to Claude Code, use the exec tool with the bash command, specifying the working directory and the task as a string. Claude Code will run with --print --permission-mode bypassPermissions automatically.
bash workdir:/path/to/project command:"claude --permission-mode bypassPermissions --print 'your coding task here'"
Examples
-
build a feature:
bash workdir:~/projects/my-app command:"claude --permission-mode bypassPermissions --print 'build a user authentication module'" -
refactor a module:
bash workdir:~/projects/my-lib command:"claude --permission-mode bypassPermissions --print 'refactor the data processing module for better performance'" -
review a pull request:
bash workdir:/tmp/pr-review command:"claude --permission-mode bypassPermissions --print 'review the changes in pull request #123 and provide feedback'"
Usage Guidance
This skill looks like a thin wrapper for running a local 'claude' CLI, but it forces a '--permission-mode bypassPermissions' flag (which overrides permissions) and doesn't declare the 'claude' binary dependency. Before installing or enabling it: 1) Do not allow automatic or unattended execution — require user confirmation. 2) Ask the author to remove or make the bypassPermissions flag optional and documented; never force a permission-bypass by default. 3) Ensure the agent runs in a restricted sandbox and that the 'claude' CLI is trustworthy and installed intentionally. 4) Have the skill declare the 'claude' binary as a required dependency (and justify any elevated flags). If you cannot verify those changes or you do not trust the local 'claude' executable, treat this skill as risky and do not enable it on sensitive projects or systems.
Capability Analysis
Type: OpenClaw Skill
Name: claude-delegate
Version: 1.0.0
The skill instructions in SKILL.md direct the agent to execute the Claude CLI using the `--permission-mode bypassPermissions` flag. This flag explicitly disables interactive safety prompts, allowing the delegated Claude process to perform arbitrary file modifications and command executions without user confirmation. While this is a legitimate feature for automation, recommending its use within an autonomous agent framework creates a high-risk environment where malicious or unintended actions could occur silently.
Capability Assessment
Purpose & Capability
The name/description match the instructions (delegating coding tasks to Claude Code). However the SKILL.md explicitly runs a 'claude' CLI with '--permission-mode bypassPermissions', yet the skill metadata declares no required binaries or credentials. The skill should have declared the 'claude' binary (or other runtime dependency) and must justify the permission-bypass flag; the current mismatch is unexpected.
Instruction Scope
Instructions tell the agent to run shell commands via exec (bash workdir:/path command:"claude ..."). This is coherent for a delegator, but the documentation forces the '--permission-mode bypassPermissions' flag and '--print' unilaterally. That flag appears to override safety/permission controls and effectively escalates the delegated tool's privileges; it broadens scope beyond simple code-generation and could enable access to files or actions the user's environment would otherwise block.
Install Mechanism
This is an instruction-only skill with no install spec or code files, which minimizes installation risk. There is nothing being downloaded or written by the skill itself.
Credentials
The skill requests no environment variables or credentials (which is reasonable). However it fails to declare that it depends on a local 'claude' CLI binary and on the ability to run shell commands in arbitrary working directories — both are effectively required at runtime and should be declared.
Persistence & Privilege
The skill does not request permanent 'always' presence (good), but instructing automatic use of '--permission-mode bypassPermissions' is a form of privilege escalation for the invoked tool. That increases the blast radius if the agent executes this skill autonomously or without user confirmation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install claude-delegate - After installation, invoke the skill by name or use
/claude-delegate - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Published the first version.
Metadata
Frequently Asked Questions
What is Claude Delegate?
Delegate various coding tasks to Claude Code. Use this skill when you need assistance with code generation, bug fixing, feature implementation, code review,... It is an AI Agent Skill for Claude Code / OpenClaw, with 433 downloads so far.
How do I install Claude Delegate?
Run "/install claude-delegate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Claude Delegate free?
Yes, Claude Delegate is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Claude Delegate support?
Claude Delegate is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Claude Delegate?
It is built and maintained by splicer scorn (@numbpill3d); the current version is v1.0.0.
More Skills