coding-agent-backup-fixed-2026q1Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (sp...
Install via ClawdBot CLI:
clawdbot install qczx0318/coding-agent-backup-fixed-2026q1Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Hardcoded API key or token pattern found in skill definition
AIzaSyCKWmPm...Calls external URL not in known-safe list
https://github.com/user/repo.gitUses known external API (expected, informational)
googleapis.comAI Analysis
The skill contains a hardcoded API key pattern (AIzaSyCKWmPm...) which is a credential exposure risk, but this appears to be example code rather than active credential harvesting. The external API usage (github, googleapis) is consistent with the skill's stated purpose of coding assistance and doesn't show evidence of unauthorized data exfiltration or hidden malicious instructions.
Generated May 12, 2026
A tech startup needs to refactor a large legacy codebase to improve maintainability and performance. The coding agent can be spawned in a background process with PTY mode to iteratively explore files and apply refactorings across the project.
An open-source maintainer receives multiple pull requests daily. Using the coding agent, they can review several PRs in parallel by spawning agents in temporary directories, each with its own workdir and PTY, and then collect results.
A fintech company wants to build a new feature like a dark mode toggle for their web app. The coding agent can be set up in the project directory with a one-shot command, using PTY and full-auto mode to auto-approve changes within a sandbox.
An enterprise DevOps team wants to automate PR reviews in their CI pipeline. They can use the coding agent to spawn multiple background sessions, each reviewing a different PR diff, and post comments via GitHub API.
A startup founder with minimal coding skills needs help prototyping an idea. They can use the coding agent in chat mode by creating a temporary git repo and running codex exec with a prompt, getting instant code generation with PTY for proper terminal interaction.
Offer coding agent capabilities as a subscription service to development teams. Users pay per session or a flat monthly fee to use the agent for code creation, refactoring, and review tasks.
Integrate the coding agent into existing CI/CD platforms as an add-on for automated code review and feature generation. Revenue comes from licensing the agent integration to enterprise clients.
Provide basic one-shot coding commands for free (limited usage) and premium features like background sessions, parallel reviews, and longer timeouts for paid tiers.
💬 Integration Tip
Ensure all bash commands using coding agents include pty:true to avoid hanging. For background tasks, utilize the process tool actions (poll, log, write) to monitor and interact with sessions.
Scored Jun 29, 2026
Audited Apr 16, 2026 · audit v1.0
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.