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 skills add gongxuanzhang/shengsheng-skill --skill project-doc-syncgit clone --depth 1 https://github.com/gongxuanzhang/shengsheng-skillWrote 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/gongxuanzhang/shengsheng-skill/project-doc-sync)<a href="https://agentmods.dev/skills/gongxuanzhang/shengsheng-skill/project-doc-sync"><img src="https://agentmods.dev/badge/skills/gongxuanzhang/shengsheng-skill/project-doc-sync/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/gongxuanzhang/shengsheng-skill/project-doc-sync"><img src="https://agentmods.dev/badge/skills/gongxuanzhang/shengsheng-skill/project-doc-sync.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 | $0.00078 | $0.02407 |
| Opus 5 | $0.00039 | $0.01203 |
| Sonnet 5 | $0.00016 | $0.00481 |
| Haiku 4.5 | $0.00008 | $0.00241 |
Grade A, and why
project-doc-sync 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 11d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Doc Sync — 项目文档自动同步
在开发对话过程中，自动维护项目的 todo.md（待办清单）和 CLAUDE.md（行为指令集），确保项目文档与实际开发进度始终一致。
CLAUDE.md 定位：行为指令集（类似给新工程师的 onboarding checklist），而非架构知识库。≤ 200 行。
职责
- todo.md 追加：对话中讨论出新的待办事项 → 自动追加到
todo.md - todo.md 删除：某个 TODO 被确认完成 → 从
todo.md中删除该条目，重新编号 - CLAUDE.md 更新：对话中确认了新的开发规范、架构决策、踩坑经验 → 更新
CLAUDE.md对应章节 - 内容外置建议：当 CLAUDE.md 内容过于详细或超过 200 行时，建议用户将详情移到
docs/并用@引用
触发场景
触发 todo.md 追加
对话中出现以下信号时触发：
- 明确讨论出需要执行的任务清单（"我们需要做 X、Y、Z"）
- 用户要求 "记一下" / "加到 todo" / "这个后面做"
- 代码审查或排查中发现需要修复的问题
- 实现过程中发现衍生任务（"这个先不改，记下来"）
触发 todo.md 删除
- 某项任务的代码已实现并验证通过
- 用户明确确认 "这个做完了" / "已经解决"
- 代码审查中发现 TODO 对应的功能已经存在
触发 CLAUDE.md 更新
- 讨论并确认了新的架构决策（且该决策影响日常开发行为）
- 新增了开发规范、代码约定
- 新增了故障排查经验（踩坑记录）
- 构建/测试/部署命令发生变更
- 发现 Claude 反复犯同样的错误（需要记录为 Gotcha）
- 项目有非常规约定需要告知 Claude
不触发 CLAUDE.md 更新
- 新增了 API 端点、DTO、Entity、Controller、Service 文件（Claude 可以从代码读取）
- 新增了配置项（Claude 可以从配置文件读取）
- 修改了状态机、业务流程（Claude 可以从代码读取）
- 纯粹的代码编写（无新决策、无新任务）
- 用户只是在提问、查阅信息
- 修改了代码但不涉及架构变更（bug 修复、重命名等）
执行步骤
todo.md 追加流程
- 读取 当前
todo.md获取现有结构和最大编号 - 判断分类：新任务属于哪个分区（🔴 上线必需 / 🟡 应该修复 / 🟢 改进优化）
- 编写条目：按标准格式编写新条目（见 reference/todo-format.md）
- 追加：在对应分区末尾追加新条目，编号递增
- 告知用户：简要说明 "已追加 TODO-N: xxx 到 todo.md"
todo.md 删除流程
- 读取 当前
todo.md - 定位 已完成的条目
- 删除 该条目的完整内容（标题 + 所有子项）
- 重新编号：后续条目编号向前顺延，保持连续
- 告知用户：简要说明 "已从 todo.md 删除 TODO-N: xxx"
CLAUDE.md 更新流程
- 内容筛选（新增 — 最关键的一步）：
- 自问："没有这行，Claude 读代码后还会犯错吗？" → 不会就不加
- Claude 可以从代码/配置文件直接读取的信息 → 不加
- 语言/框架的默认约定 → 不加
- 只有影响日常开发行为且无法从代码推断的内容才写入
- 读取 当前
CLAUDE.md完整内容 - 定位 需要更新的章节（按通用章节模型匹配，见 reference/claude-md-format.md）
- 更新内容：
- 使用指令风格编写（"做 X 时必须 Y"，而非"X 是什么"）
- 新增章节 → 追加到合适位置
- 修改现有内容 → 原地替换
- 长度检查：
- 统计更新后 CLAUDE.md 总行数
- ≤ 150 行：正常
- 151-200 行：提醒用户"接近上限，建议审视是否有可外置的内容"
- > 200 行：必须精简——将详细内容外置到
docs/并用@引用
- 渐进式披露：
- 如果待写入内容超过 5 行，考虑外置到
docs/或.claude/rules/ - CLAUDE.md 中只保留一行指令摘要 +
@引用
- 如果待写入内容超过 5 行，考虑外置到
- 扫描关联文档：检查是否需要同步更新被引用的外部文档
- 告知用户：简要说明 "已更新 CLAUDE.md: xxx"
What ships with it
8 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.
- 11d ago First seen · 182 lines · 78 tokens per session scan A a25913bcb812
project-doc-sync is a skill published in the GitHub repository gongxuanzhang/shengsheng-skill (10 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 2,407 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.