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 majiayu000/spellbook --skill weeklygit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/weekly)<a href="https://agentmods.dev/skills/majiayu000/spellbook/weekly"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/weekly.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.01353 |
| Opus 5 | $0.00020 | $0.00677 |
| Sonnet 5 | $0.00008 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
weekly 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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
生成周报
根据用户提供的日期范围 $ARGUMENTS，收集 om-generator 前后端两个仓库的工作记录，生成周报文档。
步骤 1：解析日期范围
从 $ARGUMENTS 中提取起止日期。支持格式：
2-1到2-7→ 2026-02-01 ~ 2026-02-071-27到2-2→ 2026-01-27 ~ 2026-02-022026-02-01到2026-02-07→ 完整日期- 无参数 → 默认本周一到今天
将解析结果存为变量 DATE_START 和 DATE_END（格式 YYYY-MM-DD）。年份默认 2026。
步骤 2：收集 Git 提交记录
先获取当前用户名：
git config user.name
然后分别从两个仓库收集该用户在日期范围内的提交：
前端仓库：
git -C $HOME/Desktop/code/work/mutil-om/om-generator-web log --author="<用户名>" --after="<DATE_START>" --before="<DATE_END + 1天>" --oneline --no-merges --all
后端仓库：
git -C $HOME/Desktop/code/work/mutil-om/om-generator log --author="<用户名>" --after="<DATE_START>" --before="<DATE_END + 1天>" --oneline --no-merges --all
对每个有意义的提交，用 git show --stat <hash> 查看改动范围。
步骤 3：收集 Claude Code 会话记录
读取两个项目的 sessions-index.json：
- 前端：
~/.claude/projects/<om-generator-web 绝对路径转义>/sessions-index.json - 后端：
~/.claude/projects/<om-generator 绝对路径转义>/sessions-index.json
注：Claude Code 把项目 cwd 绝对路径转义为目录名（
/替换为-），例如$HOME/Desktop/code/work/mutil-om/om-generator→-Users-<用户名>-Desktop-code-work-mutil-om-om-generator。
JSON 结构为 { version, entries: [{ sessionId, summary, firstPrompt, created, modified, gitBranch, messageCount }] }。
过滤 created 或 modified 在日期范围内的会话，提取 summary 和 firstPrompt。
步骤 4：收集 Codex 会话记录
遍历日期范围内每天的 Codex 会话目录：
~/.codex/sessions/2026/MM/DD/*.jsonl
对每个 JSONL 文件，读取第一行（type: session_meta），检查 payload.cwd 是否包含 om-generator。
如果匹配，提取：
payload.cwd— 工作目录（区分前端/后端）payload.timestamp— 会话时间payload.git.branch— 分支
然后读取文件中 type 为 message 且 payload.role 为 user 的第一条消息作为会话主题。
步骤 5：补充本机会话/记忆记录
如果当前环境提供可用的记忆搜索工具或本机记忆索引，搜索日期范围内与 om-generator 相关的记录，并把有明确证据的 session 摘要和工作记录补充到周报中。
如果没有可用的记忆工具，不要阻塞生成；在“数据来源”里写明未使用记忆补充数据。
步骤 6：分类整理
将所有收集到的信息按以下类别分类：
- 架构重构 — 代码结构调整、模块拆分、技术债清理
- 新功能 — 新增的用户可见功能
- Bug 修复 — 问题修复
- 研究与设计 — 技术调研、方案设计、原型验证
- 其他 — 文档、配置、依赖更新等
每个条目包含：
- 简短描述（一句话）
- 涉及的仓库（前端/后端/两者）
- 关键改动文件（可选）
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.
- 4d ago First seen · 148 lines · 41 tokens per session scan A 491bfac28d86
weekly is a skill published in the GitHub repository majiayu000/spellbook (276 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,353 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 2026-09-03.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
handoff
Write a portable, secret-scrubbed handoff doc so this work can continue in any AI tool or on any machine. Use when saying "handoff", "running out of tokens", or "continue elsewhere".
lov-gh-tidy
Interactive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a summary of each with analysis, then asks the user how to handle each item (close, merge, comment, delete, keep). Executes all chosen actions via gh CLI. Use when the user says "清理 GitHub", "tidy repo", "clean…
session-handoff-resume
Skill to save ultra-compact project checkpoints and seamlessly resume work across accounts or new chat sessions with minimum token consumption / Skill untuk menyimpan checkpoint proyek yang super ringkas dan melanjutkan pekerjaan secara efisien saat ganti akun/sesi tanpa boros token.
ag-teleportar
Switch rapido entre projetos no workspace com contexto preservado. Carrega CLAUDE.md, detecta stack, verifica .env, mostra branch atual, e resume estado. Nao e cd — e context-aware switching.
task-copilot
Use when work should be tracked with tc, including creating PRDs, tasks, handoffs, logs, and work products, or when preserving detailed outputs outside the chat context.