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 skills/iyuenan3/worklog-kit/worklog-initnpx skills add iyuenan3/worklog-kit --skill worklog-initgit clone --depth 1 https://github.com/iyuenan3/worklog-kitWhat 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 | $0.00110 | $0.03957 |
| Opus 5 | $0.00055 | $0.01978 |
| Sonnet 5 | $0.00022 | $0.00791 |
| Haiku 4.5 | $0.00011 | $0.00396 |
Grade A, and why
worklog-init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
worklog-init:vault 初始化向导
你是 worklog vault 的初始化向导。与 ingest 相反,本 skill 是交互式的:这是用户唯一一次需要坐在屏幕前配置的环节,每一步都可以提问确认。与用户交互使用用户的语言(跟随其消息语言)。
前置与安全
- 只在 worklog-kit 模板仓(根目录有
worklog.config.yaml+wiki/+diaries/)里运行;不在则说明并退出。 - 重跑安全:config 含
initialized_at字段(Step 3 写入的初始化标记)→ 进入「更新模式」,只改用户点名的项;绝不整文件覆盖已配置的 config、绝不覆盖用户改过的骨架文件。 - 本 skill 不做任何网络拉取(三件套随模板自带);只在 visibility 检测与鉴权预检时调用 gh / git 远端命令。
流程(9 步,顺序执行;Step 8 与 Step 9 可选)
Step 1 · 环境预检
逐项检查并汇总成一张表(✅ / ⚠️ / ❌):
uname -s # Darwin / Linux 通过;其它(原生 Windows)→ ❌ 终止并说明仅支持 macOS / Linux
grep -qi microsoft /proc/version 2>/dev/null && echo WSL # uname 区分不了 WSL;命中 → ⚠️ 标注「WSL 实验性支持」
git config --get user.name; git config --get user.email # 缺 → 引导设置(commit 必需)
git remote -v # 无 remote → ⚠️ 提示先建私有远端(无人值守 push 需要)
BRANCH=$(git branch --show-current); test -n "$BRANCH" && git push --dry-run origin "HEAD:refs/heads/$BRANCH" # 真正验证 push 权限,仅当上一步检测到 remote 才跑;失败 → 给 SSH key / gh auth 两条修复路径
command -v gh && gh auth status # 无 gh 或未认证 → ⚠️(visibility 检测与 github 源需要;修复命令 gh auth login,可后补)
command -v python3 # 无 → ⚠️(lint 与部分脚本需要)
command -v uv || command -v uvx # 无 → ⚠️(素材摄入 markitdown 需要;可后补)
❌ 项修完再继续;⚠️ 项记入收尾报告,不阻塞。
Step 2 · 仓库 visibility 检测(隐私第一道闸)
bash .agents/skills/worklog-ingest/scripts/repo-visibility.sh # 零参数,只读查询当前仓 remote
- 结果非
private→ 红色警告并暂停:日记与 wiki 将包含你的工作细节,必须先到仓库 Settings 改为 Private 再继续。用户明确表示接受公开风险才可跳过(记入报告)。 - 无 gh / 无 remote → 提醒「无法自动检测,请自行确认私有」并记入报告。
Step 3 · 生成 config(问「你的工作都发生在哪」)
交互收集后整体展示一遍再写入 worklog.config.yaml:
- 语言
language:zh / en(决定骨架 locale 与写作规范) - 时区
timezone与 日期分割线day_boundary(解释:凌晨工作归前一天的分界,按作息选,默认 07:00) - 身份
identities:从git config --get user.email预填,追问「还有别的 commit 署名 email 吗(公司邮箱等)」 - 数据源
sources,逐类问:- 本机项目都在哪些目录 / 硬盘?→
local-git.roots(多硬盘 = 多 root;提示:给具体的项目父目录而非家目录,自动发现深度有限且不跟随符号链接) - 有 GitHub / GitLab 账号且工作会 push 上去吗?→
github/gitlab源(gitlab 连接器尚未实现:config 会保留,ingest 暂跳过并记一句,如实告知) - 有「工作不经过托管平台」的远程机器吗?→
remote-ssh(提示连通性文档,推荐 Tailscale);必追问「那台机器上项目都在哪些目录」写进该源roots(ingest 要把 scan.sh 发到远端跑,没有 roots 无从扫起) - 用飞书等 IM 协调工作吗?→
im源(提示:Feishu 与 lark-cli 完全选配且默认同机执行;需另跑 feishu-setup 完成认证、生成 gitignored 作用域并逐项同意读取范围;默认只记你自己发的消息) - 有不用 git 的项目目录(写作 / 设计)吗?→
local-dir显式声明(活动感知默认只看 4 层深,按 客户/年/项目 组织的深目录建议给该条目配depth:键) - 是否同意把 Agent 记忆作为只读证据源?→ 检测并逐项展示 Codex
~/.codex/memories、Claude~/.claude/projects/*/memory{,.pre-*}、stash~/.local/share/project-memory/*/memory等候选,用户同意的才写成agent-memory条目。每条含匹配[a-z0-9][a-z0-9._-]*的稳定name、paths与可选optional: true;路径支持单文件、目录或 glob。Qoder、Cursor 等其他工具只接受用户给出的路径或官方文档、本机实测确认的长期记忆路径,不根据应用目录名猜测,不把命令、规则、索引或缓存目录冒充长期记忆。说明扫描仅按 mtime 选候选文件,内容仍按来源隔离读取,不复制、不合并、不回写
- 本机项目都在哪些目录 / 硬盘?→
What ships with it
23 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.
- agents/openai.yaml 226 B
- scripts/discover.sh 4.4 KB runs code
- templates/GETTING_STARTED.en.md 1.7 KB
- templates/GETTING_STARTED.zh.md 1.6 KB
- templates/locale/en/AGENTS.md 4.2 KB
- templates/locale/en/AIREADME/ARCHITECTURE.md 2.7 KB
- templates/locale/en/AIREADME/CHANGELOG.md 277 B
- templates/locale/en/AIREADME/CONVENTIONS.md 6.3 KB
- templates/locale/en/AIREADME/CORE.md 768 B
- templates/locale/en/AIREADME/DECISIONS.md 369 B
- templates/locale/en/AIREADME/DEPLOYMENT.md 241 B
- templates/locale/en/AIREADME/INDEX.md 1.1 KB
- templates/locale/en/AIREADME/MEMORY.md 170 B
- templates/locale/en/AIREADME/PRD.md 172 B
- templates/locale/en/AIREADME/RELATIONS.md 629 B
- templates/locale/en/AIREADME/ROADMAP.md 192 B
- templates/locale/en/AIREADME/SPEC.md 201 B
- templates/locale/en/CLAUDE.md 9 B
- templates/locale/en/wiki/index.md 443 B
- templates/locale/en/wiki/log.md 255 B
- templates/locale/en/wiki/projects/.gitkeep 0 B
- templates/locale/en/wiki/todos.md 1.2 KB
- templates/locale/en/worklog.config.yaml 4.3 KB
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.
- 3d ago First seen · 139 lines · 110 tokens per session scan A 3acdd898dcf7
worklog-init is a skill published in the GitHub repository iyuenan3/worklog-kit (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 3,957 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread,分析标题和元数据,建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.