agpairDelegate coding work to Antigravity through agpair CLI: dispatch a task, wait for EVIDENCE_PACK or COMMITTED, inspect doctor/daemon health, review logs, or s...
Install via ClawdBot CLI:
clawdbot install logicrw/agpairGrade 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/logicrw/agpairAudited Apr 18, 2026 · audit v1.0
Generated May 21, 2026
A lead developer delegates a coding task to Antigravity via agpair, then reviews the evidence pack and approves or requests changes. This streamlines pair programming by separating controller and executor roles.
Before dispatching tasks, the user runs agpair doctor and daemon status to ensure the repository bridge is healthy. This prevents errors from desktop_reader_conflicts or session issues.
When a task is dispatched with --wait, the agent actively polls until a terminal state (EVIDENCE_PACK or COMMITTED). This ensures no premature intervention and accurate completion reporting.
After receiving an EVIDENCE_PACK, the user inspects task logs and status, then chooses continue, approve, reject, or retry. This structured feedback loop improves code quality.
With trigger phrases in English and Chinese, this skill enables cross-cultural teams to delegate coding tasks seamlessly, e.g., '派任务' to dispatch work to Antigravity.
Charge developers or teams a monthly fee for using agpair to delegate tasks to Antigravity, including health monitoring and evidence review features.
Charge per task dispatched via agpair, with tiers for complexity or wait duration. Encourages usage while providing predictable costs.
Offer agpair as part of an enterprise AI coding agent package, including priority support, custom health checks, and compliance features.
💬 Integration Tip
Ensure the absolute repo path is correctly specified for doctor checks, and avoid sending semantic actions while active waiters exist.
Scored May 21, 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.
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.