Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/an8079/take-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/an8079/take-skills/takes-auto-interview)<a href="https://agentmods.dev/commands/an8079/take-skills/takes-auto-interview"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-auto-interview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/an8079/take-skills/takes-auto-interview"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-auto-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00832 |
| Opus 5 | $0.00020 | $0.00416 |
| Sonnet 5 | $0.00008 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
auto-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/auto-interview - 双 Agent 辩论式访谈
两个 AI Agent 互相辩论，从产品经理（逆向思维）和架构师（传统思维）两个角度设计方案。
使用方式
/auto-interview
或
自动访谈
头脑风暴
双Agent访谈
辩论访谈
参与者
| Agent | 角色 | 思维方式 |
|---|---|---|
| Agent A | 产品经理 | 逆向思维 (Working Backwards) |
| Agent B | 架构师 | 传统思维 (正向设计) |
Agent A - 产品经理 (Working Backwards)
从用户价值和业务目标出发：
- 用户真正需要什么？
- 成功标准是什么？
- 如何验证成功？
Agent B - 架构师 (传统思维)
从技术可行性和系统设计出发：
- 技术上如何实现？
- 架构是否合理？
- 有哪些技术风险？
工作流程
用户输入想法
↓
┌─────────────────────────┐
│ Agent A (PM) 提出方案 │
│ 逆向思维，PR/FAQ格式 │
└───────────┬─────────────┘
↓
┌─────────────────────────┐
│ Agent B (架构师) 评审 │
│ 技术可行性分析 │
└───────────┬─────────────┘
↓
┌─────────────────────────┐
│ 辩论回合 │
│ 双方就分歧点辩论 │
└───────────┬─────────────┘
↓
达成共识？
↓ ↓
是 否
↓ ↓
生成规格 继续辩论
↓
用户审核确认
输出内容
详细规格文档
比 /deep-interview 更详细的技术架构框架：
| 内容 | 说明 |
|---|---|
| 产品概述 | PR/FAQ 格式的产品描述 |
| 技术架构 | 系统架构图、模块划分 |
| 数据流设计 | 数据存储、流转、接口 |
| API 设计 | 详细接口规范 |
| 部署方案 | 部署架构、环境配置 |
| 风险评估 | 技术风险及应对 |
辩论记录
- 双方观点摘要
- 分歧点及解决过程
- 最终共识
与 /structure_thinking 的关系
| 维度 | /auto-interview | /structure_thinking |
|---|---|---|
| 时机 | 需求阶段，生成规格 | 规格确定后，分析架构 |
| 目标 | 生成产品规格 | 评估架构质量 |
| 特点 | 双 Agent 辩论 | 顶级架构师视角 |
两者独立，用户手动选择使用哪个。
用户同意机制
- 生成规格后 - 需要用户审核确认
- 用户可修改 - 可以要求重新讨论某些点
- 确认后 - 进入计划/实现阶段
提示： 当你有一个相对清晰的想法但不知道如何设计时，使用 /auto-interview。两个 Agent 会帮你从不同角度思考并达成最佳方案。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 115 lines · 40 tokens per session scan A b43a20014139
auto-interview is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 832 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.