ifixai-ai / iFixAi
本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。
English · 简体中文 · 日本語 · 한국어 Catch your agent’s mistakes and blind spots before the shit hits the fan. Quick start • Three ways to run • Test your agent • Scoring • Audit recorded actions • Docs • Contributing
在问题爆发前，捕捉你代理（Agent）的错误和盲点。快速入门 • 三种运行方式 • 测试你的代理 • 评分 • 审计记录的操作 • 文档 • 贡献
What it is The existing Eval, Red-teaming, and Observability Tools are evaluating the agent mainly based on tech capability (token efficiency, latency, prompt injections). They cannot answer the most crucial question. Is the agent doing the job it is supposed to do based on the business KPIs and Organizational Structure? iFixAi gives you this answer in less than 120 seconds by striking the right balance between AI-Red Teaming and Operational Assurance. Adversarial depth. Assurance discipline. All-in-one auditing process.
它是什么？现有的评估（Eval）、红队测试（Red-teaming）和可观测性工具主要基于技术能力（Token效率、延迟、提示词注入）来评估代理。它们无法回答最关键的问题：代理是否根据业务KPI和组织架构完成了它应该做的工作？iFixAi通过在AI红队测试和运营保障之间取得适当平衡，在不到120秒内为你提供答案。对抗深度。保障准则。一体化审计流程。
Three ways to run All three run the same diagnostic underneath. The difference is how you configure and drive it. CLI: guided wizard CLI: explicit flags Plugin or Skill How you drive it ifixai setup once → ifixai run zero-flag every time; config saved to ifixai.yaml pass every option as a CLI flag; fully scriptable the agent is the operator: discovers your setup, builds the fixture, runs it, and explains the scorecard Best for first-time users, fast repeatable runs, team onboarding CI, automation, audit-ready scripted batches a guided, explained run with an interactive scorecard, inside the agent you already use
三种运行方式：这三种方式底层运行相同的诊断程序，区别在于配置和驱动方式。CLI：引导式向导；CLI：显式标志；插件或技能。驱动方式：ifixai setup一次 → 每次运行无需标志（ifixai run）；配置保存至ifixai.yaml。将每个选项作为CLI标志传递；完全可脚本化。代理即操作员：发现你的设置、构建测试环境、运行并解释评分卡。适用场景：首次用户、快速重复运行、团队入职；CI、自动化、审计就绪的脚本化批处理；在现有的代理中使用带有交互式评分卡的引导式解释运行。
Setup pip install “ifixai[
设置：pip install “ifixai[
What you test any provider, or your agent’s real endpoint same same Who grades it self, one independent vendor, or a multi-judge ensemble same same Output JSON + Markdown reports + rich terminal scorecard same interactive results artifact (+ JSON source of truth; static-report fallback) Suite pick with arrow keys in the wizard 10 inspections by default; —full-run for all 60, or —suite smoke|strategic|essential|core|extended|all the agent picks —mode/—suite, same engine as the CLI Works in any terminal any terminal / CI Claude Code, Cursor, Codex, VS Code, Windsurf, Cline, Continue, Gemini, Zed
测试内容：任何提供商或你代理的真实端点（相同）。评分者：自我评分、独立供应商或多裁判组合（相同）。输出：JSON + Markdown报告 + 丰富的终端评分卡（相同，交互式结果工件 + JSON事实来源；静态报告回退）。套件：在向导中用箭头键选择；默认10项检查；—full-run运行全部60项，或—suite smoke|strategic|essential|core|extended|all；代理选择—mode/—suite，与CLI引擎相同。运行环境：任何终端；任何终端/CI；Claude Code, Cursor, Codex, VS Code, Windsurf, Cline, Continue, Gemini, Zed。
Quick start Explore business-policy compositions: Policy Lab finds shortest harmful sequences of permitted actions and checks permission repairs against legitimate completion goals. Includes an offline refund-store example and explicit local-callable replay. Now try it yourself. Pick a path from the table above; full walkthrough: docs/get-started.md.
快速入门：探索业务策略组合：策略实验室（Policy Lab）寻找允许操作中最短的有害序列，并针对合法的完成目标检查权限修复。包含一个离线退款商店示例和显式的本地可调用重放。现在亲自尝试一下。从上表中选择一条路径；完整演练请见：docs/get-started.md。
Guided wizard (recommended) pip install “ifixai[openai]” # or anthropic, gemini, etc.: install the provider extra you’ll test ifixai setup # arrow-key wizard: pick provider, model, judge, suite → writes ifixai.yaml ifixai run # no flags needed; reports land in ./ifixai-results/ ifixai setup detects API keys already in your environment and surfaces them at the top of each prompt. No key found? The wizard tells you which env var to export; if it’s still missing when you run, you’ll be prompted for it before the first API call. Windows note: if PowerShell can’t find ifixai after pip install, add Python’s Scripts\ folder to your PATH, or run it as python -m ifixai. This is the usual Python-on-Windows PATH gap, not an iFixAi issue.
引导式向导（推荐）：pip install “ifixai[openai]“（或anthropic, gemini等：安装你要测试的提供商扩展）；ifixai setup（箭头键向导：选择提供商、模型、裁判、套件 → 写入ifixai.yaml）；ifixai run（无需标志；报告存放在./ifixai-results/中）。ifixai setup会检测你环境中已有的API密钥，并在每个提示的顶部显示。未找到密钥？向导会告诉你需要导出哪个环境变量；如果运行时尚未找到，系统会在第一次API调用前提示你输入。Windows注意事项：如果pip安装后PowerShell找不到ifixai，请将Python的Scripts文件夹添加到PATH，或以python -m ifixai运行。这是Windows上Python常见的PATH缺失问题，并非iFixAi的问题。
Plugin (Claude Code and Codex) The recommended way to run from an agent: a one-time native install with an auto-provisioning hook, so there is nothing to set up per run. Ask in plain English (“run iFixAi on my setup”) and the agent discovers your config, builds the fixture, names the cost before anything is billed, runs the diagnostic on the model(s) and judge(s) you pick, then walks you through the scorecard.
插件（Claude Code和Codex）：从代理运行的推荐方式：一次性原生安装，带有自动配置钩子，因此无需每次运行都进行设置。用简单的英语提问（“run iFixAi on my setup”），代理会发现你的配置、构建测试环境、在计费前预估成本、在你选择的模型和裁判上运行诊断，然后带你查看评分卡。
Claude Code, from inside Claude Code: /plugin marketplace add ifixai-ai/iFixAi /plugin install ifixai@ifixai-community Then ask “run iFixAi on my setup”, or type /ifixai:ifixai. (Restart Claude Code or run /reload-plugins if it doesn’t appear.) Already on ifixai@ifixai-ai? That keeps working, and to move to the new marketplace name you run /plugin marketplace remove ifixai-ai first, then the two commands above.
Claude Code，在Claude Code内部：/plugin marketplace add ifixai-ai/iFixAi；/plugin install ifixai@ifixai-community。然后询问“run iFixAi on my setup”，或输入/ifixai:ifixai。（如果未出现，请重启Claude Code或运行/reload-plugins）。已经在用ifixai@ifixai-ai？它仍可工作，若要迁移到新的市场名称，请先运行/plugin marketplace remove ifixai-ai，然后执行上述两条命令。
Codex, in your terminal: codex plugin marketplace add ifixai-ai/iFixAi codex plugin add ifixai@ifixai-community Then start Codex and ask “run iFixAi on my setup”. Codex asks once to trust the plugin’s hook, then provisions the engine on the first session. Already on ifixai@ifixai-ai? codex plugin marketplace upgrade fails on the renamed marketplace, so run codex plugin marketplace remove ifixai-ai first, then the two commands above.
Codex，在你的终端中：codex plugin marketplace add ifixai-ai/iFixAi；codex plugin add ifixai@ifixai-community。然后启动Codex并询问“run iFixAi on my setup”。Codex会询问一次是否信任插件钩子，然后在第一次会话中配置引擎。已经在用ifixai@ifixai-ai？codex plugin marketplace upgrade在重命名的市场上会失败，因此请先运行codex plugin marketplace remove ifixai-ai，然后执行上述两条命令。
Skill (every agent) Prefer a single scaffolded file, or use an agent without a plugin? One zero-install command writes a native /ifixai-skill slash command into any agent: Claude Code, Codex, Cursor, VS Code / Copilot, Windsurf, Cline, Continue, Gemini, or Zed (plus an AGENTS.md bridge). Only uv and Python 3.10+ are needed; no API key or provider extra to scaffold: uvx ifixai install —agents cursor # any slug: claude, codex, vscode, windsurf, cline, continue, gemini, zed uvx ifixai install —agents all # scaffold every agent at once uvx ifixai install —list # every supported agent and where its file lands
技能（每个代理）：更喜欢单个脚手架文件，或者使用的代理没有插件？一条零安装命令即可将原生的/ifixai-skill斜杠命令写入任何代理：Claude Code, Codex, Cursor, VS Code / Copilot, Windsurf, Cline, Continue, Gemini或Zed（外加一个AGENTS.md桥接）。仅需uv和Python 3.10+；无需API密钥或提供商扩展即可构建：uvx ifixai install —agents cursor（任何slug：claude, codex, vscode, windsurf, cline, continue, gemini, zed）；uvx ifixai install —agents all（一次性构建所有代理）；uvx ifixai install —list（查看每个支持的代理及其文件位置）。
Then run /ifixai-skill in that agent. It reads your setup, builds the fixture, shows the cost via a free —dry-run, and runs only after you say yes (the run is zero-install too, driving uvx —from “ifixai[
然后在该代理中运行/ifixai-skill。它会读取你的设置、构建测试环境、通过免费的—dry-run显示成本，并仅在你确认后运行（运行也是零安装的，驱动uvx —from “ifixai[
Explicit flags # 1. Install the CLI + the extra for the provider you’ll test pip install “ifixai[anthropic]” # 2. Prove the pipelin
显式标志：# 1. 安装CLI + 你要测试的提供商扩展：pip install “ifixai[anthropic]”；# 2. 验证流水线