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 vincent-wen789/claude-briefing-cards --skill briefing-cardgit clone --depth 1 https://github.com/vincent-wen789/claude-briefing-cardsWrote 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/vincent-wen789/claude-briefing-cards/briefing-card)<a href="https://agentmods.dev/skills/vincent-wen789/claude-briefing-cards/briefing-card"><img src="https://agentmods.dev/badge/skills/vincent-wen789/claude-briefing-cards/briefing-card/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/vincent-wen789/claude-briefing-cards/briefing-card"><img src="https://agentmods.dev/badge/skills/vincent-wen789/claude-briefing-cards/briefing-card.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 | $0.00246 | $0.07986 |
| Opus 5 | $0.00123 | $0.03993 |
| Sonnet 5 | $0.00049 | $0.01597 |
| Haiku 4.5 | $0.00025 | $0.00799 |
Grade A, and why
briefing-card 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 12d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
briefing-card 汇报卡
🔴 状态（2026-06-14 起）· 冻结开发，进入真实使用检验 功能完整（三类卡 + T0–T3 路由 + 自动/手动触发 + 安全层）· 5 轮独立 review 过 · darwin 86.8。唯一缺口是真实使用 = 0，所有「好用 / 触发准 / 体验顺」的结论都来自 subagent 模拟。 除非 Vincent 撞到真实场景的具体问题（该画没画 / 卡点着别扭 / 触发漏了），否则不要再加功能、不要再 review——边际收益已递减，复杂度利息在涨（110 行 + CLAUDE.md 两段，今天连改文件都出过「报 success 没落地」的乌龙）。下一个改动应由真实使用反馈驱动，不由「还能更完善」驱动。
⚠️ 装到别的机器（触发引擎不在本文件）
本 skill 的自动触发靠 CLAUDE.md 里 ## 汇报卡 briefing-card（自动触发） 那段，不在 SKILL.md。只 copy 本文件夹 → 只剩手动触发（出个卡 / 回传），自动出卡失灵（Vincent 2026-07-06 实测撞到）。装机：① copy 文件夹到目标机 ~/.claude/skills/ ② 把 claude-md-block.md 里 8< 之间的段落粘进目标机 CLAUDE.md。
Overview
用聊天内渲染的 HTML 卡片替代纯文字，做决策请求和进度汇报。两个核心价值：模板强制完整（固定区块逼着填全信息）+ 决策按钮闭环（点按钮 = 回传决策，消灭误解）。颗粒度路由是灵魂——画错时机比不画更糟。
T0–T3 路由（先过这道闸再动手）
| 档 | 形式 | 条件 |
|---|---|---|
| T0 | 普通文字 | 一句话能说清 / 单一事实 / 闲聊。绝不画卡 |
| T1 | AskUserQuestion | 2-4 个选项，每项利弊一行讲得清，不需要图/链接 |
| T2 | 聊天内卡片（本 skill 主体） | 决策需多维对比/证据链接/内联数据图形；进度 ≥3 条线或含 blocker；pending 确认 ≥3 项且每项带出处（≤2 项走文字或 AskUserQuestion） |
| T3 | HTML 文件 | 要存档 / 发给别人 / 要看内容图 / 超约两屏 → 转 huashu-design |
默认翻转（2026-06-18 · Vincent 第一条真实使用反馈：手动召唤太累、触发太怂）：一旦判定本轮属于汇报 / 进度 / 决策 / 选项 / 确认 / 拍板场景，默认假设落 T2 出卡——举证责任反过来：不再问「够不够得上 T2」，而是问「能不能安全降到 T0/T1」。只有①一句话能说清 / 单一事实 / 闲聊 → 降 T0；②2-4 个选项且每项利弊压得进一行、不需图/链接 → 降 T1。两条都不满足就出卡，别再犹豫。翻转的是判定倾向，不是取消节流：防卡墙节流（硬规则那条，1 小时 ≥2 张卡自动降文字）仍然全程生效，被卡片刷屏的风险由它兜底——所以放心偏向出卡。
从 T0 往上判断，停在第一个满足的档。T1 vs T2 拿不准：把每个选项压成一行（利弊 + 改动量 + 介入点）——全部压得进且不需要链接/图 → T1；任何一个选项压不进一行，或需要链接/图/对比表 → T2。注意：改动量本身不构成推力（「跨 3 文件」塞得进一行），是「装不下」才推 T2。
T2 vs T3 边界（任一命中即 T3）：
- 要存档复用，或要发给 Vincent 以外的人
- 内容里有需要看内容的图（截图 / 照片 / 设计稿）——无论文件多小一律 T3：聊天内卡片受 CSP 沙箱限制，外部图床和本地图片都加载不出来，且卡内小窗看不清细节。仅装饰/识别用途的小图（logo、icon，几 KB 级 base64 内嵌）可留 T2。数据类可视化不算图：进度条、对比条形、趋势迷你图应该用内联 SVG/CSS 直接画进 T2 卡里——「有图可看」优先靠原生图形实现，不是一律踢去 T3
- 按模板填完预计超过约两屏、需要滚动阅读。一到两屏之间先砍信息密度或拆成两张卡留在 T2，实在装不下才升 T3
T3 注意两点：① 文件里没有 sendPrompt 回传——决策类内容升 T3 时，文件只承载详情（图、长对比、引用全文），决策收口仍回聊天（文件 + 一张轻量 T2 决策卡或 T1 选项卡）；② 产出走 huashu-design，给出文件路径并直接帮 Vincent 在浏览器打开。
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.
- 12d ago First seen · 273 lines · 246 tokens per session scan A a87b46952ec6
briefing-card is a skill published in the GitHub repository vincent-wen789/claude-briefing-cards (1 stars, last pushed 1mo ago), licensed MIT. It adds 246 tokens to every session and 7,986 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
notifications
Send notifications through the unified notification router.
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
start-the-day
An on-demand personal daily briefing — weather, headlines, the shape of your day, and one thing worth your attention — in a sharp executive-assistant voice. The general-purpose morning brief; richer work or admin digests compose it as their general layer.
career-portfolio
A portfolio-building skill for Korean job seekers that organizes projects and explains their work for development, design, marketing, and planning roles.