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-updatenpx skills add iyuenan3/worklog-kit --skill worklog-updategit clone --depth 1 https://github.com/iyuenan3/worklog-kitWrote 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/iyuenan3/worklog-kit/worklog-update)<a href="https://agentmods.dev/skills/iyuenan3/worklog-kit/worklog-update"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/worklog-update.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 | $0.00113 | $0.01819 |
| Opus 5 | $0.00056 | $0.00910 |
| Sonnet 5 | $0.00023 | $0.00364 |
| Haiku 4.5 | $0.00011 | $0.00182 |
Grade A, and why
worklog-update 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
worklog-update:skill 升级器
与用户交互的语言跟随其消息语言。安全边界(hard deny):只写 vault 的
.agents/skills/白名单路径、项目级.claude/skills兼容软链接,以及已安装的全局~/.agents/skills/{aireadme,stash,pitfalls}与对应~/.claude/skills/兼容软链接。diaries/、wiki/、inbox/、两层 config、AIREADME/、根文档、~/.local/share/project-memory/、~/.local/share/pitfalls-memory/与~/.local/share/worklog/memory/一律不碰;.claude/settings.json只展示 diff 供 Claude Code 用户手动决定。
前置
.ingest.lock存在 → 拒绝运行(等 ingest 跑完)。- upstream 默认
https://github.com/iyuenan3/worklog-kit(config 顶层键upstream_repo可覆盖,适配 fork 用户;模板注释里有示例)。
流程
- 取版本:
git ls-remote --tags --refs --sort=-version:refname <upstream> 'v*',只接受首个符合v<数字>.<数字>.<数字>的 release tag;无 tag(上游 pre-alpha 期)→ 明确告知「没有可锁定 release tag,main 是持续变化的非 release 版本」,经用户确认后才用 main,不确认则干净退出。不得按文本顺序猜“最新”,也不得把 annotated tag 的^{}行当成版本。 - 浅克隆到临时目录:
git clone --depth 1 --branch <tag> <upstream> <scratch 临时目录>(绝不git remote add/git merge,上游历史不进用户仓)。 - 兼容形态预检:当前标准形态是
.agents/skills/实体目录 +.claude/skills -> ../.agents/skills软链接。若本地仍是旧版.claude/skills/实体目录,先列出迁移计划,经确认后将它整体移动到.agents/skills/,再建立并验证兼容软链接;若两边同时是实体目录,拒绝自动合并,先让用户决定保留哪份,避免覆盖本地改动。 - 差异盘点:白名单 = 上游
.agents/skills/下全部子目录。逐 Skill 与本地diff -rq分类,列出新增(上游新 Skill,供用户选择装不装)/ 有变更(明确列出「本地存在但上游已移除」的文件,镜像同步会移走它们)/ 本地独有 Skill(用户自己加的,永不动)。内容级审计:对「有变更」Skill 里的 SKILL.md 与脚本类文件(*.sh/*.py),逐个diff -ru展示实际改动内容再请求确认(这些是将被 agent 执行的指令与代码,只报文件名不构成 §12 说的人工审计点);摘录上游AIREADME/CHANGELOG.md相关段给用户看「这次更新带来什么」(kit 发布史与 vault 版本流合在该文件,读上游 clone 里的那份、不动本地)。再单列已安装全局三件套与本轮 vault 新版之间的差异,明确它们会随本轮一起刷新;全局目标内有用户修改时,同样展示内容级 diff,不可把它当普通旧副本静默覆盖。 - 确认后同步:逐 Skill(或用户说全部)做镜像同步。先在临时目录准备上游副本并验证
SKILL.md,再把本地目录移动到同一临时目录作可恢复备份,最后把新目录移动到.agents/skills/<name>/;任一步失败立即把备份移回,不留下半套状态。用户在该 Skill 目录内自加过文件的,在 Step 4 已看到移出清单、确认才动;本地独有 Skill 与一切用户数据不动。注意:worklog-lint 与 worklog-ingest 共享校验脚本(标点门 / 日期门在 ingest 目录),两者建议成对升级;locale 模板在 worklog-init 目录内,随该 Skill 一起同步。 - 刷新全局三件套:只处理
aireadme/stash/pitfalls。若~/.agents/skills/<name>已是指向当前 vault.agents/skills/<name>的正确软链接,只验证并保留。若是实体目录,按 Step 4 已确认的 diff 执行「新副本预校验 → 旧目录移入临时备份 → 从 vault 新版完整复制 → 校验失败则恢复」,不得用cp -R合并。若是指向其他 canonical 的软链接,先报告目标,只有用户确认切换来源才替换。最后确保~/.claude/skills/<name> -> ../../.agents/skills/<name>,实体目录或错误链接仍按同一备份、确认与恢复纪律处理。全程不得读取、移动或重建任何~/.local/share/*memory*数据。 - config schema 检查:比对上游模板
worklog.config.yaml的schema_version与本地:上游更新则列出需补的键 + 默认值。实施口径:一律只展示、不代写(config 在上方 hard deny 清单内):顶层键给出可直接粘贴的追加块(含注释),嵌套键(modules 子键、sources 条目属性)以 diff 形式标注应插入的层级(盲 append 会破坏 YAML 结构);用户明确说「帮我改」才代改并逐键复述。绝不覆盖已有值。 - 兼容 dry-run:跑
python3 .agents/skills/worklog-lint/scripts/lint.py验证契约锚点仍匹配;验证项目级.claude/skills解析到.agents/skills,再验证全局 Codex 与 Claude Code 三件套入口最终读取同一份实现;🔴 则输出手动调整清单。 - 收尾:commit(
chore: skill 升级至 <tag>)+ 校验通过后清理临时备份 + 报告(升级了什么 / 跳过了什么 / 全局三件套状态 / settings diff 提示 / 需要手动做的)。
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.
- 3d ago First seen · 32 lines · 113 tokens per session scan A b07637d2cd3b
worklog-update is a skill published in the GitHub repository iyuenan3/worklog-kit (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,819 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…