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.
npx agentmods add skills/telagod/code-abyss/generating-docsnpx skills add telagod/code-abyss --skill generating-docsgit clone --depth 1 https://github.com/telagod/code-abyssWhat 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 | $0.00034 | $0.00908 |
| Opus 5 | $0.00017 | $0.00454 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
generating-docs 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 2d 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
造典关卡 · 文档生成器
生成的是骨架，不是答案。填决策理由是人的工作，工具不能代劳。
何时使用
| 场景 | 跑 | 理由 |
|---|---|---|
| 新模块创建后第一时间 | ✅ | 趁记忆新鲜填决策 |
| verifying-modules 报「缺 README/DESIGN」 | ✅ | 直接补救 |
| 重构后边界变化 | ⚠ | 看是否要重生成或手动改；不要 --force 覆盖已有内容 |
| 已有完整文档 | ❌ | 不要破坏人工写的内容 |
生成内容
README.md（自动可填部分）
| 字段 | 自动来源 | 待人补 |
|---|---|---|
| 模块名 | 目录名 | 是否有更好的展示名 |
| 描述 | 顶级 docstring（Python） | 「存在理由」必须人写 |
| 特性 | TODO（占位） | 列 3–5 个核心能力 |
| 依赖 | requirements.txt / package.json / Cargo.toml 等 |
是否有运行时假设 |
| 使用方法 | TODO（占位） | 5 分钟跑通示例 |
| API 概览 | 公开类/函数签名 | 调用顺序、生命周期 |
| 目录结构 | tree 输出 |
— |
DESIGN.md（骨架占位）
| 字段 | 自动 | 待人补（最重要） |
|---|---|---|
| 设计目标 / 非目标 | TODO | 核心决策驱动力 |
| 架构 | TODO | 含一张图最好 |
| 核心组件 | 公开类/函数列表 | 各组件的协作关系 |
| 决策表 | TODO | 方案对比 + 选择理由 |
| 技术选型 | 依赖列表 | 选 X 不选 Y 的理由 |
| 权衡 | TODO | 牺牲了什么 |
| 安全考量 | TODO | 信任边界、威胁模型 |
语言支持
| 语言 | 提取深度 |
|---|---|
| Python | 类、函数、docstring、依赖（最完整） |
| Go / TypeScript / Rust | 目录结构 + 依赖 |
| 其他 | 基础目录结构 |
流程
doc_generator.js 生成骨架
↓
人工填 TODO（决策理由、使用示例、非目标）
↓
verify-module 校验完整性
↓
通过则提交
何时不要 --force
- 目标文件已有人工内容 ——
--force会无差别覆盖。先 diff 旧版，手动合并。 - CI 环境 —— 生成应在开发机做，CI 只校验，不生成。
与其他 skill 联动
- 跑完后 → 必跑 verifying-modules
- 大模块 → 拆分前先 designing-architectures 想清楚边界
使用
node scripts/doc_generator.js <模块路径>
node scripts/doc_generator.js <模块路径> --force # 强制覆盖（慎用）
node scripts/doc_generator.js <模块路径> --json # CI 用
收口
工具给骨架，TODO 不补完不算交付。生成后 5 分钟内人工填决策；超过 1 天会忘原因，文档质量陡降。
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.
- 2d ago First seen · 90 lines · 34 tokens per session scan A 4846edf5000e
generating-docs is a skill published in the GitHub repository telagod/code-abyss (240 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 908 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 2026-08-30.
Other skills, from other repositories
codexkit-a-b-test-planner
Design rigorous A/B test plans with hypothesis, sample size calculation, Minimum Detectable Effect (MDE), randomization strategy, and decision rules. Includes guardrail metrics and rollout playbook. Use when planning product experiments, conversion optimization, or data-driven feature decisions.
codexkit-api-design-reviewer
Review REST and GraphQL API designs for consistency, usability, and best practices. Covers naming conventions, versioning strategy, error format, pagination, authentication patterns, and breaking change detection. Use when reviewing API specs, designing new APIs, or auditing existing endpoints.
codexkit-architecture-decision-writer
Write Architecture Decision Records (ADRs) following the Michael Nygard format. Captures context, options considered, decision rationale, and consequences. Use when making technology choices, framework selections, or any architectural decision that future developers need to understand.
codexkit-audit-readiness-checker
Assess organizational readiness for financial audits (internal or external). Map assertions to account balances, check evidence completeness, score readiness using a Red/Amber/Green framework, and generate a remediation timeline. Aligned with SOX, IFRS, and GAAP audit standards. Use before scheduled audits or when…
codexkit-business-case-writer
Write structured business cases with problem framing, options analysis, financial modeling (NPV/ROI/Payback), risk assessment, and implementation roadmap. Follows HBR business case structure. Use when seeking budget approval, proposing new initiatives, or justifying investment decisions.
codexkit-campaign-brief-writer
Write agency-standard creative briefs for marketing campaigns. Structure Background, Objective (SMART), Target Audience persona, Key Message, Mandatories, KPIs, Timeline, and Budget Allocation. Use when briefing agencies, creative teams, or internal marketing on a new campaign.