lucky-coding-agentDelegate 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 rmbell09-lang/lucky-coding-agentGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/user/repo.gitAudited Apr 17, 2026 · audit v1.0
Generated Oct 5, 2026
Startup engineering teams delegate building new features (e.g., a dark mode toggle or an authentication module) to Codex or Claude Code agents running in background sessions. Developers monitor progress via the process tool, ask clarifying questions through stdin, and merge the resulting code after review. This reduces context-switching and accelerates sprint velocity.
Open-source maintainers or platform teams use the 'batch PR reviews' pattern to spawn one Codex agent per PR in background PTY sessions, each reviewing a diff against main. Reviewers collect logs, poll status, and merge feedback, cutting review backlog from days to hours while keeping the main workspace untouched via temp clones or git worktrees.
Enterprise teams point coding agents at a specific workdir using PTY and background mode to refactor large modules (e.g., auth services or API layers) without letting the agent wander into unrelated files. The workdir constraint and git-initialized scratch repos keep agent context tight and prevent accidental side effects in sensitive repositories.
Indie hackers and solo devs use `mktemp -d && git init && codex exec` to spin up scratch projects for quick experiments, prototypes, or one-shot code generation without polluting their main project. The temp git repo satisfies Codex's trusted-directory requirement and keeps throwaway work isolated.
Engineering teams facing complex bugs use background Codex sessions with full-auto sandboxing to iteratively explore a codebase, trace issues, and propose fixes. Since agents can read files and run commands within the workdir, they effectively act as autonomous debuggers that report findings via session logs for human verification.
A subscription SaaS that wraps the coding-agent skill with dashboards, session history, and team-level quotas, letting engineering orgs delegate tasks to Codex, Claude Code, or Pi agents from a single interface. It abstracts PTY, background process management, and workdir isolation behind a polished UI.
A service that automatically spawns a fleet of Codex agents to review every incoming PR, aggregating findings into actionable comments on GitHub or GitLab. Customers pay per repository or per PR reviewed, and the service handles temp clones, worktrees, and parallel session orchestration.
An on-prem or VPC-deployed platform that gives enterprises governed access to coding agents with audit logs, sandbox policies, role-based workdir permissions, and integration with internal Git servers. It targets regulated industries that cannot send code to external SaaS tools.
💬 Integration Tip
Always run coding agents with `pty:true` and a scoped `workdir` to avoid broken output and context leakage. For PR reviews, never use the host project folder—clone to a temp dir or use git worktree to keep the main workspace intact.
Scored Jun 29, 2026
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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.