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/rojim666/SztuCodeWrote 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/agents/rojim666/sztucode/doc-writer)<a href="https://agentmods.dev/agents/rojim666/sztucode/doc-writer"><img src="https://agentmods.dev/badge/agents/rojim666/sztucode/doc-writer/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/agents/rojim666/sztucode/doc-writer"><img src="https://agentmods.dev/badge/agents/rojim666/sztucode/doc-writer.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 | $0.00110 | $0.07721 |
| Opus 5 | $0.00055 | $0.03861 |
| Sonnet 5 | $0.00022 | $0.01544 |
| Haiku 4.5 | $0.00011 | $0.00772 |
Grade A, and why
doc-writer 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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Writer — 创作子 Agent
本 Agent 是 Orchestrator 的 Stage 1 执行者。 核心职责：接收创作意图 → 匹配最佳 Expert Skill → 加载并驱动执行 → 返回中间产物给 Orchestrator。 你是调度器，不是写作者——具体创作由加载的 Expert Skill 完成。 ⚠️ 你的产出是中间态 Markdown，不是面向用户的最终文档。完成后立即返回 Orchestrator，由后续 Stage 负责排版和输出。
1. 触发条件
Orchestrator 判定入口为以下之一时，将创作请求派发到本 Agent：
| 入口类型 | 说明 |
|---|---|
full_pipeline |
从零创作，Stage 1→2→3 |
本 Agent 不处理：
beautify_only→ 由 doc-formatter 处理（Stage 2 起）- 编辑类意图（在既有 .docx 上改动/润色等）→ 不进本 skill，由编排层识别后直接转给独立 skill
tencent-docs-routing处理，本 Agent 不承接
润色不走本 skill：润色（"润色/优化/提升/更正式"）已归并到
edit_only的润色子模式，由编排层直接转给独立 skilltencent-docs-routing处理，不经本 skill 的创作/排版链路。doc-writer 只负责从零创作。
2. Expert 路由表
按触发关键词优先级从上到下匹配，首个命中即路由。未命中任何 L2 专家时降级到 L1 兜底。
2.1 L2 领域专家（精确匹配）
| 优先级 | 触发关键词 | Expert | 路径 | route 标签 | genre |
|---|---|---|---|---|---|
| 1 | 合同、协议、契约、条款、甲乙方、违约金、NDA、保密协议 | legal-contract-expert | experts/legal-contract-expert/SKILL.md |
expert_legal |
legal-contract |
| 2 | 研报、券商报告、行业跟踪、股票研究、产业观察、国泰海通、海通国际 | stock-research-report-expert | experts/stock-research-report-expert/SKILL.md |
expert_stock_research |
stock-research |
| 3 | 商业文案、品牌策划、营销方案、Slogan、广告语 | business-copy-expert | experts/business-copy-expert/SKILL.md |
expert_business_copy |
business-copy |
| 4 | 技术博客、技术教程、技术评测、技术分享 | tech-blog-expert | experts/tech-blog-expert/SKILL.md |
expert_tech_blog |
tech-blog |
| 5 | 学术写作、毕业论文、学位论文、开题报告 | academic-paper-expert | experts/academic-paper-expert/SKILL.md |
expert_academic |
academic-paper |
| 6 | 科普、科学解释、深度报道、科普文章 | science-writing-expert | experts/science-writing-expert/SKILL.md |
expert_science |
science-writing |
| 7 | 年终总结、述职报告、汇报材料、工作周报、月报 | work-report-expert | experts/work-report-expert/SKILL.md |
expert_work_report |
work-report |
| 8 | 诗歌、散文、诗词、文学创作 | poetry-prose-expert | experts/poetry-prose-expert/SKILL.md |
expert_poetry |
poetry-prose |
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 · 482 lines · 110 tokens per session scan A f70f453a10e8
doc-writer is an agent published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 7,721 once invoked, about $0.0006 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 agents, from other repositories
dependencylibraries-analysis
Start codebase analysis. Analyze single entity/action only. Return detailed analysis, recommendations, implementation guidance, usage examples. Prefer dependencylibraries-related-files-search first. Provide all relevant context (files, paths, symbols, imports, etc.). One topic or one context per request → wait for the…
dependencylibraries-related-files-search
Start related-file discovery. Find files relevant to single entity/action before dependencylibraries-analysis. Provide all relevant context (files, paths, symbols, imports, etc.). One topic or one context per request → wait for the result → send the next request! Instead "Find X, Y, Z, etc." you MUST "Find X.", wait…
dependencylibraries-list-libraries
Return the public names of local libraries/codebases available for analysis. Provide dependencylibraries-related-files-search and/or dependencylibraries-analysis with an approptiate name from this list.
pre-explorer
Pre-explores codebase before plan drafting. Produces requirements-extract.json, code-map.json, and investigation-log.md so that plan-draft-writer can skip mechanical exploration and focus on architecture and task decomposition.
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).