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/commands_index)<a href="https://agentmods.dev/commands/an8079/take-skills/commands_index"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/commands_index/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/commands_index"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/commands_index.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 | $0.00000 | $0.01224 |
| Opus 5 | $0.00000 | $0.00612 |
| Sonnet 5 | $0.00000 | $0.00245 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
COMMANDS_INDEX 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令索引
版本： v3.1.0 | 更新日期：2026-03-24 项目路径：
F:\claude-studio\3.4\claude-studio\claude-studio
核心命令（8个）
| 命令 | 文件 | 用途 | 阶段 |
|---|---|---|---|
/interview |
interview.md | 需求访谈 | 访谈 |
/spec |
spec.md | 生成规格文档 | 规格 |
/plan |
plan.md | 创建实现计划 | 计划 |
/code |
code.md | 进入编码模式 | 编码 |
/tdd |
tdd.md | TDD 工作流 | 编码 |
/test |
test.md | 运行测试 | 测试 |
/review |
review.md | 代码审查 | 审查 |
/debug |
debug.md | 调试模式 | 调试 |
增强命令（3个）
| 命令 | 文件 | 用途 |
|---|---|---|
/takes-analyze |
takes-analyze.md | 项目分析 |
/takes-scope |
takes-scope.md | 范围管理 |
/takes-import |
takes-import.md | 导入项目 |
自动模式命令（4个）
| 命令 | 文件 | 用途 |
|---|---|---|
/takes-autopilot |
takes-autopilot.md | 自动驾驶模式 |
/takes-ultraqa |
takes-ultraqa.md | QA 测试模式 |
/takes-ultrawork |
takes-ultrawork.md | 高效工作模式 |
/takes-team |
takes-team.md | 团队协作模式 |
专项命令（17个）
| 命令 | 文件 | 用途 |
|---|---|---|
/takes-boss |
takes-boss.md | 老板督导 PUA 模式 |
/takes-reverse-architect |
takes-reverse-architect.md | 逆向思维架构师 |
/takes-po |
takes-po.md | 提示词优化器 |
/takes-imapo |
takes-imapo.md | AI 图像提示词工程师 |
/takes-qa |
takes-qa.md | 自动化 QA 测试与修复 |
/takes-qa-only |
takes-qa-only.md | 仅生成缺陷报告 |
/takes-rag |
takes-rag.md | RAG 检索增强 |
/takes-pua |
takes-pua.md | PUA 模式 |
/takes-office-hours |
takes-office-hours.md | 办公时间 |
/takes-structure-thinking |
takes-structure-thinking.md | 结构化思考 |
/takes-find-product-remind |
takes-find-product-remind.md | 产品提醒 |
/takes-test-teams |
takes-test-teams.md | 团队测试 |
/takes-ralph |
takes-ralph.md | Ralph 循环模式 |
/takes-deep-interview |
takes-deep-interview.md | 深度访谈模式 |
/takes-auto-interview |
takes-auto-interview.md | 自动访谈模式 |
/takes-notify |
takes-notify.md | 通知管理 |
触发词映射
| 触发词 | 命令 |
|---|---|
开始访谈 |
/interview |
写规格 |
/spec |
做计划 |
/plan |
开始编码 |
/code |
TDD |
/tdd |
跑测试 |
/test |
审查代码 |
/review |
调试 |
/debug |
分析 |
/takes-analyze |
范围 |
/takes-scope |
导入 |
/takes-import |
深度访谈 |
/takes-deep-interview |
快速开始 |
/interview 快速开始 |
pua |
/takes-pua |
团队 |
/takes-team |
qa |
/takes-qa |
ultrawork |
/takes-ultrawork |
autopilot |
/takes-autopilot |
ultraqa |
/takes-ultraqa |
ralph |
/takes-ralph |
boss |
/takes-boss |
逆向 |
/takes-reverse-architect |
po |
/takes-po |
imapo |
/takes-imapo |
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.
- 9d ago First seen · 133 lines · 0 tokens per session scan A d40d773d8022
COMMANDS_INDEX is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,224 tokens. 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.