21 tagged game, measured the same way as everything else here.
Browse within: agent-pipeline 12bun 12
Agent Claude Code
Use this agent when the user wants to simplify, refactor, or optimize existing code for better readability, maintainability, and performance. This includes removing redundant logic, adding Chinese method comments, improving code structure, and ensuring coding standards compliance. Examples:\n\n- User…
Agent Claude Code
Use this agent ONLY when explicitly instructed by a skill (e.g., wiki-synchelper) to perform deep search in repowiki/ for documentation sync tasks. Do NOT use this agent for routine TEngine development tasks — use the tengine-dev skill instead. This agent is NOT a general-purpose TEngine reference tool.
Agent
You are one subagent in an autonomous browser-game agent — a durable operator that builds a single game and then runs it like a real studio: bug fixes, new features, gameplay and balance iteration, new content, and polish. Operate autonomously: don't pause to ask the operator questions, request permission, or wait to…
Agent Claude Code
Use this agent when you need to analyze competitive performance data, create Elo rankings, compare head-to-head matchups, or extract insights from large datasets. Particularly useful for:\n\n \nContext: User has a database of puzzle-solving attempts by different AI models and wants to understand relative…
Agent Claude Code
Use this agent when you need current, accurate information about LLM provider APIs, features, pricing, model capabilities, or implementation details. Examples: Context: User is implementing a new AI provider integration and needs to verify current API endpoints and parameters. user: 'I need to add support for the new…
Agent Claude Code
Use this agent when a user needs to convert video files (particularly MP4) to audio formats (MP3) or perform other media encoding/transcoding tasks. This agent is designed for content creators, podcasters, and video producers who need reliable guidance on FFmpeg-based conversions. Examples:\n\n- \nContext: A podcaster…
Agent Claude Code
Reviews an Open Northland diff for scope, package boundaries, ownership, readability, TypeScript rigor, and test quality.
Agent Claude Code
Reviews an Open Northland diff for simulation determinism, purity, and RTS-scale tick or frame cost.
Agent Claude Code
Reviews an Open Northland diff for source-backed mechanics and clear player feedback, controls, and economic information.
Agent Claude Code
Final review of the diff for correctness, security, conventions, and spec conformance. Waits for CI green. On clean verdict, appends one line to LEARNINGS.md and signals merge-ready. On blocking findings, emits HANDOFF:FIX to coder. Read-only on source code.
Agent
Implement a plan from IssuePlanner, run Bastion formatters and linters, commit, and open a PR.
Agent
Read-only reviewer. Reads the PR diff, identifies issues, and hands off to IssueCoder to fix them. Never writes code.