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 anneheartrecord/charles-skill --skill weread-digestgit clone --depth 1 https://github.com/anneheartrecord/charles-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/anneheartrecord/charles-skill/weread-digest)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/weread-digest"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/weread-digest/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/anneheartrecord/charles-skill/weread-digest"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/weread-digest.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 | $0.03230 |
| Opus 5 | $0.00055 | $0.01615 |
| Sonnet 5 | $0.00022 | $0.00646 |
| Haiku 4.5 | $0.00011 | $0.00323 |
Grade A, and why
weread-digest scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "https://i.weread.qq.com/api/agent/gateway" \ How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
weread-digest — 微信读书沉淀
Overview
微信读书里的划线和想法是原料，知识库笔记是复用资产，推文是一次性产物。这个 skill 把三者串成一条固定顺序的流水线：先落笔记，再出推文。
笔记先落盘，是因为推文只用得上一本书里的三五个判断，剩下的读完就丢了。笔记留住全部，下次写别的选题还能取。
两段流水线
第一段（必做）：微信读书 → 20-knowledge/读书/读书笔记/读《书名》小记.md
第二段（按需）：那篇笔记 → 30-outputs/tweets/ 推文草稿
用户只说「整理成笔记」就停在第一段。说「写成推文」也要先跑完第一段——笔记不存在时不许直接从划线写推文，那样这本书的原料只被消费一次。
第一段：落知识库笔记
1. 定位 bookId
- 用户给了书名 →
/store/search，取bookId - 用户问「哪些书还没写笔记」「最近读了什么没记」→ 走下面的缺口盘点
1b. 缺口盘点（口径别搞窄了）
拉源：/user/notebooks，游标分页——首页只传 count，之后取上一页 books 最后一项的 sort 当 lastSort 再请求，直到 hasMore 为 0。不要传 offset/limit，那两个参数后端不读，会一直返回第一页。
排序：books[].sort 就是最近一次做笔记的时间戳。用户说「最近」时按它倒序，别按书架顺序。
比对时必须扫全四个位置，只扫 读书笔记/ 会产生大量假缺口（实测 269 本「缺口」里有相当一部分是这四类）：
| 位置 | 形态 | 注意 |
|---|---|---|
20-knowledge/读书/读书笔记/ |
读《X》小记.md |
主目录 |
20-knowledge/网络书籍/<书名>/ |
result.json + MANUAL_REVIEW.md |
另一套导入产物，不是 md 笔记 |
_private/阅读/ |
X-读书笔记-YYYY-MM-DD.md |
在 gitignore 区，rg 必须加 --no-ignore，否则搜不到 |
30-outputs/tweets/、30-outputs/长文/ |
推文/长文里直接引用了书名 | 没笔记但已经消费过，不该再报成缺口 |
书名匹配要容错，实测踩过的坑：
- 一字之差：微信读书《以日为镜》vs 库里《以日为鉴》。别只做精确/子串匹配，长度 ≥3 的标题要允许 1 个字的差异
- 副标题与后缀：
长得好看能当饭吃吗：提升认知的33个经济学常识、（第2版）、（微信读书特别版）、（全六册）、文件名里的 z-library 后缀，比对前全部剥掉 - 拿不准的不要直接判缺口，列进「待人工确认」那一档
盲区（要说出来，不要假装覆盖了）：/user/notebooks 只返回有笔记数据的书。用户读完但一条划线都没划的书，这条路径发现不了，得另走 /shelf/sync 看 finishReading 与 readingProgress。
2. 拉原料（两个接口都要拉）
| 接口 | 拿到什么 | 在笔记里变成什么 |
|---|---|---|
/book/bookmarklist |
updated[].markText 划线原文 + chapters[] 章节 |
章节结构 + 加粗的要点行 |
/review/list/mine |
reviews[].review.content 本人想法与点评 |
要点下面的展开段落 |
调用规范（鉴权、参数平铺）见 weread-skills skill，不在这里重复。
**skill_version 不要在本文件里写死。**每次请求都要带，值取 weread-skills/SKILL.md 顶部 frontmatter 的 version 字段，现读现取。回包里出现 upgrade_info 时按它的 message 先完成升级再重跑——这是 weread-skills 的硬规则，不是建议。（本文件下面 Quick Reference 里的版本号只是示例，照抄会过期。）
必须走 gateway 接口，不要用 weread MCP 的 weread_notes 工具。实测那个工具返回的是全书热门划线（items[].userVid 是别人、items[].totalCount 是划线人数），不是本人划线。拿它当个人笔记写出来的note 是别人的阅读痕迹。判别方法：回包里有 userVid 且各不相同的，就是热门划线。
What ships with it
1 file 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.
- 10d ago First seen · 161 lines · 110 tokens per session scan A aef9f7e03be9
weread-digest is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 3,230 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
lecture-to-notes
A workflow that turns lecture or conference recordings into organised notes using local transcription and slide extraction. It accepts video and audio files, including MOV, MP4, M4A, MP3, and WAV.
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
textbook-to-md
Convert PDF/EPUB textbooks to searchable markdown files for an AI agent's own reference. Use this skill whenever: (1) the user asks to convert a textbook/PDF chapter to markdown, (2) you need to search textbook content and no markdown version exists yet, (3) batch-converting a set of reference books into a knowledge…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…