GetTokens

GetTokens 领域工程：账号池、quota、UI 体系、调试与 CLIProxyAPI fork。

GetTokens 流程治理：Wails 开发回路、spaces、文档记忆写回与 AGENTS 同步。

GetTokens Codex 账号列表：Codex Channel Routing、账号请求顺序、两模式路由、路由探测、模型映射、OAuth 透传语义、openai-compatible 映射保存与浏览器预览。

GetTokens CLIProxyAPI 上游版本 intake / reference-port 工作流：看新 tag、规划合并、拆子 space、在 gettokens/sidecar 内重实现、验证、重建 sidecar、dev App 验收与双仓提交。

Use when dxyer iOS verification, smoke testing, or debugging needs real API traffic evidence through Proxyman CLI: clear sessions, discover proxy host, export HAR/proxymansession logs, inspect request headers, verify DXY-TOD-SESSION user switching, or distinguish API data mismatch from UI/function failure.

GetTokens 性能治理：用于排查或预防内存占用、WebView/Wails 卡顿、React 渲染放大、大账号池请求放大、sidecar Go 热路径、日志/SQLite/本地文件膨胀、性能回归、perf budget 或 profiling 验收；当用户说性能、内存、卡顿、占用、峰值、泄漏、慢、回归、治理、budget、pprof、profiling，或改动触及账号池、quota、live sessions、session-management、usage attribution、sidecar management API、Wails bridge、日志热路径时使用。

GetTokens 桌面/Wails 前端设计质量统一 skill，合并 taste-skill、Impeccable 与 frontend-system-design 的可复用方法。Use when designing, shaping, auditing, polishing, hardening, or system-designing GetTokens frontend/Wails surfaces: UI/UX flows, Gemini/frontend handoff briefs, visual anti-pattern audits, state/DTO/routing/performance checklists, desktop previews, screenshots, and frontend acceptance criteria. 适用于前端体验优化、视觉重构、复杂页面系统设计、设计稿落地、审计页面、发布前 harden；不用于纯后端/sidecar 修复。

Use when wiring Open Design into this project or agent workflow, including `od` daemon health checks, CLI/API/MCP setup, Skills and design-system registry inspection, media generation, or project artifact reads.

GetTokens Codex 二进制管理：Codex CLI 版本源、下载、激活、回退、托管 PATH、release cache、版本说明和紧凑列表 UI。

GetTokens 会话管理插件契约：修改会话分析/复盘/导出类插件结果字段、Wails DTO、dev bridge、前端映射和验收时使用。

Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.

GetTokens 项目级 Codex subagent 生命周期治理：创建、拆分、合并、删除、TOML 校验、文档记忆写回。

Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.

GetTokens Claude Code 账号列表：Claude Channel Routing、Anthropic 格式账号筛选、请求顺序、两模式路由、项目绑定兼容边界、路由探测、模型映射、官方默认模型 profile 与 local apply 边界。

GetTokens Codex Skills / MCP 扩展管理：源码校准解析、全局 Skill roots、MCP section/tool 语义、Git source、UI 验收与整理拆分。

GetTokens macOS 发版流程：版本同步、提交 tag、Release workflow、Sparkle appcast、官方 DMG 下载验收、memory 写回。

Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project. Use when you need a from-scratch macOS app layout, SwiftPM targets/resources, a custom .app bundle assembly script, or signing/notarization/appcast steps outside Xcode.

Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask 出方案/给方案/深入分析/怎么设计/有没有必要/值不值得/plan this/how should I/should we keep this for features, architecture, or value judgments. Not for bug fixes or small edits.

Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/检查pi/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users ask 排查/报错/崩溃/不工作/回归/判断为什么报错, or say something used to work and now fails. Not for code review or new features.

Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask 学习一下/深入研究/研究一下/整理成文章/deep dive/compile sources or need one coherent reference from many inputs. Not for quick lookups or single-file reads.

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask 看这个链接/读一下/read this/check this URL. Not for local text files already in the repo.

Rewrites and polishes prose in Chinese or English, removing AI-like wording while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask 帮我写/改稿/润色/去AI味/写一段/审稿/tweet/rewrite/proofread. Not for code comments, commit messages, or inline docs.