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 agents/vod-studio/violet/docs-mapgit clone --depth 1 https://github.com/VOD-Studio/violetWhat 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 | $0.00000 | $0.00997 |
| Opus 5 | $0.00000 | $0.00498 |
| Sonnet 5 | $0.00000 | $0.00199 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
docs-map 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 yesterday.
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
文档责任地图
功能/模块增删、架构变更时,按下表同步对应文档;提交前核对。地图本身描述「哪类变更归哪个文档」,与具体功能无关,新增文档种类时在此登记一行。
| 变更类型 | 需同步的文档 | 同步内容 |
|---|---|---|
| 新功能/新模块上线 | 根 README.md |
「功能特性」列表加一行能力级描述(不列实现细节) |
| 后端新模块(domain 新目录) | api/README.md |
模块清单、端点表、目录结构说明(若有) |
| 前端新 feature 目录 | web/README.md |
目录结构说明与 feature 清单(若有) |
| 架构调整(分层/装配方式变化) | AGENTS.md 架构节 + 根 README.md 技术栈表 |
两处必须同一次提交内一致 |
| 新增/变更 MCP server | docs/guides/mcp-servers.md |
server 清单与能力描述 |
| 部署/发版流程变化 | docs/deploy/release-runbook.md |
流程步骤与拓扑图 |
| 新增面向开发者的指南 | docs/README.md |
文档索引登记 |
下线功能
删除模块时反向执行:从上述文档移除对应条目;迁移历史(api/migrations/)与 ADR(docs/adr/)是 append-only 记录,不回改。
判定
- 只改 bug/重构/改内部实现 → 不动文档。
- 用户可感知的能力变化(新页面、新端点、新配置项) → 必须同步。
- 拿不准 → 按「新读者能否凭文档正确理解系统现状」判定。
新建文档决策
默认不新建文档——代码、commit message、AGENTS.md 能承载的不另立文件。仅以下情况新建,先在此表登记再动笔:
| 情况 | 文档类型 | 落点 | 判据 |
|---|---|---|---|
| 做了难以逆转的技术选型,「为什么选 X 不选 Y」未来会被问 | ADR | docs/adr/NNN-slug.md |
决策一旦反悔成本高 |
| 团队要反复遵守的代码约定 | guide | docs/guides/ |
第三个人会写错的地方 |
| 有人要照着执行的操作流程(部署/配置/联调) | guide/runbook | docs/guides/ 或 docs/deploy/ |
有明确步骤可照做 |
| 功能开发前的需求拆解 | PRD + issues | docs/prd/ + docs/issues/ |
功能分支第一个 commit(见 AGENTS.md) |
| 单个功能的对外说明 | README 一行 | 对应 README | 不为此建新文件 |
不建:内部实现 walkthrough(代码自表达)、一次性 bug 修复过程(commit 够)、调研草稿无沉淀价值。
写作约束
读者与任务先行:动笔前能说出「这篇回答什么人的什么问题」,说不出的不写。规则:
- 具体物优先:命令、路径、代码块、表格先于抽象描述。一节里没有任何可复制执行的东西,这节是空的。
- 不复述代码:函数签名、目录清单、配置默认值由源码自表达,写进文档即缓存,必漂移。
- 禁模板结构:不写「背景/概述/核心特性/总结」四件套,不以「未来展望」收尾。
- 一句一事实:删掉任何一句不损失信息就删。特征词自查:「不仅…更…」「标志着」「致力于」「进一步提升」「强大而灵活」——出现即重写。
- 篇幅上限:README 功能一行;guide 以「一个新人能照做」为准;ADR 一页内。
- 交付前通读一遍,按
humanizer-zhskill 的清单扫 AI 痕迹(若有该 skill)。
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.
- yesterday First seen · 49 lines · 0 tokens per session scan A ab9b22863ae0
docs-map is an agent published in the GitHub repository VOD-Studio/violet (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 997 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 agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.