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 flybear16/weread-shelf --skill skillgit clone --depth 1 https://github.com/flybear16/weread-shelfWrote 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/flybear16/weread-shelf/skill)<a href="https://agentmods.dev/skills/flybear16/weread-shelf/skill"><img src="https://agentmods.dev/badge/skills/flybear16/weread-shelf/skill/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/flybear16/weread-shelf/skill"><img src="https://agentmods.dev/badge/skills/flybear16/weread-shelf/skill.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 | $0.00111 | $0.00939 |
| Opus 5.5 | $0.00044 | $0.00376 |
| Sonnet 5.5 | $0.00022 | $0.00188 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
weread-shelf 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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeRead-Shelf — SQL-ify your 微信读书
The local weread-shelf CLI is the entry point. It loads weread CLI's JSON
export into a local DuckDB cache, then exposes SQL queries.
When to use
User says:
- "查我微信读书的 XX" / "我的书架" / "完读率" / "最近读了什么"
- "用 SQL 分析我的读书数据"
- "把 weread 和 XX db 关联起来" / "join weread"
- "我的读书画像 / 统计 / 报告"
Quick Start
# 0. Verify environment
weread-shelf doctor
# 1. Pull latest shelf into DuckDB
weread-shelf sync
# 2. Run preset analysis
weread-shelf analysis
# 3. Custom SQL
weread-shelf sql "SELECT category, COUNT(*) FROM shelf GROUP BY 1 ORDER BY 2 DESC"
# 4. Cross-source join (e.g. attach xiaozhi device db)
weread-shelf join xz /path/to/xiaozhi.db
weread-shelf sql "SELECT s.title, x.last_active FROM shelf s LEFT JOIN xz.devices x ON x.user_id = s.book_id"
Pre-built Queries
Available via weread-shelf <command>:
| Command | Returns |
|---|---|
analysis |
Full portrait (overall + by-category + recent + top authors) |
sql "<query>" |
Arbitrary SQL |
export <path> --format parquet|csv|json |
Dump shelf |
join <alias> <path> |
Attach external SQLite |
The internal shelf table schema:
shelf (
book_id VARCHAR PRIMARY KEY,
title VARCHAR NOT NULL,
author VARCHAR,
category VARCHAR, -- e.g. '经济理财-管理'
finish_reading INTEGER, -- 0 or 1
read_update_at TIMESTAMP,
update_at TIMESTAMP,
cover VARCHAR,
deep_link VARCHAR
)
Cross-source Join
weread-shelf join <alias> <path-to-sqlite> attaches any local SQLite db.
Common join keys:
bookId↔ user-id in app DBs (xiaozhi, sbti-tools etc.)title↔ product-name (lowercased match)category↔ tag
Rules
- Always run
syncfirst if the user added new books since last query. - Prefer preset queries over raw SQL for simple metrics — they encode
domain knowledge (e.g. category is
'-'-delimited). - For agent use, prefer
sqlwith structured JSON output:weread-shelf sql "..." --format json --output /tmp/result.json - Cache file is local at
~/.weread-shelf/cache.duckdb. Safe to delete for a fresh re-sync. - Never write to
shelffrom MCP/SQL — read-only by design. To refresh, runweread-shelf sync.
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.
- 2mo ago First seen · 100 lines · 111 tokens per session scan A 4788c1145ce8
weread-shelf is a skill published in the GitHub repository flybear16/weread-shelf (0 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 939 once invoked, about $0.0004 per session on Opus 5.5. 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.
weread-shelf compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| weread-shelfflybear16/weread-shelf | Skill | 0 | 3mo ago | MIT | A | 111 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | 2d ago | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 924 | yesterday | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | 2d ago | Apache-2.0 | A | 63 | Claude Code, Codex |