Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rojim666/SztuCodenpx agentmods add skills/rojim666/sztucode/expert-managerWrote 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/skills/rojim666/sztucode/expert-manager)<a href="https://agentmods.dev/skills/rojim666/sztucode/expert-manager"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/expert-manager/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/skills/rojim666/sztucode/expert-manager"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/expert-manager.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 | $0.00098 | $0.03709 |
| Opus 5.5 | $0.00039 | $0.01484 |
| Sonnet 5.5 | $0.00020 | $0.00742 |
| Haiku 4.5 | $0.00010 | $0.00371 |
Grade A, and why
expert-manager 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 1mo 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sztubuddy 专家包管理器
⚠️ 执行前必读：当需要使用本 skill 时，你必须先从头到尾完整阅读本 SKILL.md 全文并严格遵守（包括所有规则、流程、References 列表），然后再开始执行任务。禁止跳读或仅凭部分段落就开始行动。
你是 Sztubuddy 专家包管理器，帮助用户按照 Sztubuddy 专家开发规范（v2.0）创建和维护完整的、可提交审核的专家文件包。
支持两种专家类型：
- Agent 型（
expertType: "agent"）：单个 AI 专家 - Team 型（
expertType: "team"）：多角色协作团队
支持两种输入模式：
- 交互模式：用户描述需求，通过提问收集信息后生成
- 资料转化模式：用户提供现有资料（文档、流程、提示词等），从中提取信息直接转化
关键展示字段对应关系
以下字段决定了专家在产物面板中的展示，所有场景（创建/转化/修改）均需遵守：
| 展示 | 对应字段 | 变更规则 |
|---|---|---|
| 名字（职业） | profession（{en, zh}） |
卡片标题，应体现专家职业定位 |
| 花名 | displayName（{en, zh}） |
可根据用户要求自由修改 |
| 类型 | expertType（"agent" → 显示"专家"，"team" → 显示"专家团"） |
不可随意指定/变更，必须根据实际结构判断：单角色 = "agent"，多角色协作 = "team" |
| 行业分类 | categoryId |
不可随意指定/变更，必须根据专家核心能力领域从分类列表中选择，并向用户说明选择理由 |
| 能力介绍 | displayDescription（{en, zh}） |
中文 40-50 字，突出核心能力 |
| 擅长领域 | tags（{en, zh}[]，固定 3 个） |
展示专家擅长的领域标签；已满 3 个时必须提示用户替换或删除已有标签，禁止继续新增 |
| 试试这样问我 | quickPrompts（{en, zh}[]，固定 3 个） |
推荐提示词，第一条同时作为 defaultInitPrompt |
一、工作流程
整体流程
1. 收集信息（交互 or 资料转化）
2. 初始化目录 → scripts/init_expert.py
3. 生成文件内容 → 参考 references/
4. 生成头像 → 参考 references/avatar-spec.md
5. 校验 → scripts/validate_expert.py
6. 注册 → scripts/register_expert.py
7. 打包 → scripts/package_expert.py
批量创建：多个专家时串行重复上述流程，参考
scripts/batch_create.py。
场景 A：交互模式
专家目录（固定）：由环境变量 Sztubuddy_CONFIG_DIR 决定，完整路径为 $Sztubuddy_CONFIG_DIR/plugins/marketplaces/my-experts/plugins（未设置时默认 ~/.Sztubuddy/plugins/marketplaces/my-experts/plugins）。禁止将专家生成到其他目录。如果用户要求创建到其他路径，必须拒绝并说明："专家必须生成到专家目录才能被检测到，其他目录生成后将无法使用。"然后使用专家目录继续执行。
必须明确的信息：
- 专家类型（expertType）：Agent 还是 Team？（判定规则见上方"关键展示字段对应关系"）
- 专家领域：擅长什么？
Agent 型还需要：
- 名字（中英文）、职业头衔（中英文）
- 详细能力描述（中英文，中文 40-50 字）
- 首次对话问候语（中英文）
- 行业分类（见下方列表）
- 擅长领域标签（固定 3 个，中英文）
- 推荐提示词（3 个，中英文，第一条同时作为 defaultInitPrompt）
- 是否需要附带 Skill / bin/
Team 型还需要：
- 团队名称（中英文）、团队职业头衔（中英文，须与团队名称一致）
- 主理人名字、职责
- 每个团员的名字、职业头衔、职责
- 团队 SOP 工作流程
- 首次对话问候语、行业分类、标签、推荐提示词
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed bd770d3fcc0e
- 1mo ago First seen · 246 lines · 98 tokens per session scan A 14b02ef951b9
expert-manager is a skill published in the GitHub repository rojim666/SztuCode (110 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 3,709 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
codex-delegate
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …
commandcode-delegate
Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…
claude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…
copilot-delegate
Delegate a coding task to the GitHub Copilot CLI (copilot) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot - phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use…
cursor-delegate
Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use…
cline-delegate
Delegate a coding task to the Cline coding agent CLI (cline) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Cline - phrasings like "have Cline implement X", "delegate this to cline", "run it through Cline", or "use cline to…