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/tdoc-orchestratorWrote 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/tdoc-orchestrator)<a href="https://agentmods.dev/skills/rojim666/sztucode/tdoc-orchestrator"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/tdoc-orchestrator/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/tdoc-orchestrator"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/tdoc-orchestrator.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 | $0.00157 | $0.05514 |
| Opus 5 | $0.00078 | $0.02757 |
| Sonnet 5 | $0.00031 | $0.01103 |
| Haiku 4.5 | $0.00016 | $0.00551 |
Grade A, and why
tdoc-orchestrator 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 today.
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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Applied Writing Orchestrator
Orchestrator = 意图识别 + 能力编排（composer，不是 lookup table）。 它自身不写作/排版/编辑，只做四件事：识别场景 → 组合 stage 能力链 → 分派子 Agent 执行 → 记录溯源。 编排层只拥有"路由 + 跨层数据衔接"；每个能力"内部怎么干、I/O 契约"由对应
agents/*.md负责，本文件不复述。
📌 承接范围：本 skill 只承接文档创作 + 排版美化 + HTML→DOCX 转换。文档编辑（在既有 .docx 上改动/润色）由独立 skill
tencent-docs-routing承接，不在本文件的编排范围内。
📁 子 Agent 路径约定：
doc-writer/doc-formatter/doc-converter三份 Agent 定义位于 plugin 根的agents/目录下。引用时统一用<plugin_root>/agents/<name>.md绝对路径锚定（<plugin_root>= plugin 根目录的绝对路径），不依赖 cwd，不要用../../agents/<name>.md相对路径。
深度工作流 reference（动手前必读 — 优先于子 Agent 委派）
下列 skill 命中条件时完整阅读并严格按步骤执行；命中后无需继续读本 SKILL.md 下文，也无需按本 skill 的子 Agent 委派流程操作——该 skill 即本轮执行的唯一依据。未命中才继续下方「意图识别与编排」。
| 优先级 | 何时加载 | 文件 |
|---|---|---|
| P0 | 短篇创作（无文档 + 创作动词 + 模型判断目标篇幅 <1000 字） | brief-compose（路径：<plugin_root>/skills/brief-compose/SKILL.md） |
意图识别与编排（唯一决策点）
Orchestrator 有调度子 Agent 的权限，按"能力组合"工作，而非穷举场景：预设只是高频组合的命名，遇到长尾场景可按编排规则自行组合。
原子能力（编排的积木 = 路由表，"执行者"列即分派目标）
| Stage | 能力 | 执行者 | 输入 → 输出 |
|---|---|---|---|
| S1 | 文档内容创作 | doc-writer |
意图 → md |
| S2 | 文档版式生成/美化 | doc-formatter |
md／内容文档 → html（恒为 html，风格由 formatter 内部按内容体裁自行决定；只做美化，不做注入） |
| S3 | 文档格式转换 | doc-converter |
html → docx（HTML→DOCX 转换 + 强制 present_files 打开预览；只做转换，不做编辑） |
各能力的内部路线与完整输入/输出契约见对应
agents/*.md（doc-writer §5/doc-formatter §2/doc-converter §4），本文件不复述字段清单。
What ships with it
2 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.
- today First seen · 218 lines · 157 tokens per session scan A 333476ab5343
tdoc-orchestrator is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 157 tokens to every session and 5,514 once invoked, about $0.0008 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 2026-09-12.
Other skills, from other repositories
Gmail, Google Calendar, Drive, Docs, Sheets and Contacts for a connected Google account: read and search mail, send and reply, book and move meetings, find files, read and write Docs and Sheets, look people up. Use whenever the user mentions their email, inbox, calendar, meetings, Drive, a Google Doc or Sheet.
opencode-export
Export opencode sessions to self-contained HTML + JSON archives for sharing, review, or backup. Use when the user wants to save, archive, or share their AI coding session history.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
co-mail-and-drive
Read and send mail from the user's own Gmail or Outlook account, safely stage Gmail draft attachments, send from the agent's own address, manage Outlook contacts and the Outlook calendar, and work with Google Drive files — with co gmail, co outlook, co email, and co gdrive. Use when the user asks about their inbox, an…
upload-artifact
Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload…