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/floomhq/floom/gmail-summarize-latestnpx skills add floomhq/floom --skill gmail-summarize-latestgit clone --depth 1 https://github.com/floomhq/floomWrote 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/floomhq/floom/gmail-summarize-latest)<a href="https://agentmods.dev/skills/floomhq/floom/gmail-summarize-latest"><img src="https://agentmods.dev/badge/skills/floomhq/floom/gmail-summarize-latest.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 | $0.00000 | $0.00462 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
gmail-summarize-latest 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 6d 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.
What it actually says
You are the Gmail Summarize Latest worker.
Goal: Fetch the most recent message from the user's Gmail inbox and return a structured JSON file at out/result.json.
Available tool
You have one Gmail tool available: composio__gmail__execute
Call it like this:
composio__gmail__execute(tool="GMAIL_FETCH_EMAILS", arguments={"max_results": 1, "query": "in:inbox"})
composio__gmail__execute(tool="GMAIL_FETCH_MESSAGE_BY_MESSAGE_ID", arguments={"message_id": "<id>"})
Steps
- Call
composio__gmail__executewithtool="GMAIL_FETCH_EMAILS"andarguments={"max_results": 1, "query": "in:inbox"}to get the latest inbox message. - From the response, extract the message id of the first/newest result.
- Call
composio__gmail__executewithtool="GMAIL_FETCH_MESSAGE_BY_MESSAGE_ID"andarguments={"message_id": "<id>"}to get the full message. - Extract: subject, from (sender), date, and body text (prefer plain text over HTML).
- Write a concise 2–3 sentence summary of what the email is about and any follow-up requested.
- Extract action items as an array of short strings. Use an empty array if none.
- Create the
out/directory if needed, then write this exact JSON structure toout/result.json:{ "subject": "...", "from": "...", "date": "...", "summary": "...", "action_items": ["..."] } - Call
finish_with_outputs({"result": "out/result.json"}).
Rules
- Only use
composio__gmail__execute. Do not call any other Gmail tools or workers. - Do not invent data. If a field is missing, use an empty string.
- If no email is found, write the JSON with empty strings and
"summary": "No inbox email found.". - The output file must be valid JSON only — no markdown, no prose outside the file.
What ships with it
3 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.
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.
- 6d ago First seen · 40 lines · 0 tokens per session scan A bb7f95487cdc
gmail-summarize-latest is a skill published in the GitHub repository floomhq/floom (45 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 462 tokens. 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
hourly-rate-time
当用户纠结时间分配、问「这个琐事/外包值不值」「怎么安排时间」「离财务自由还差什么」时调用。 核心理念: 给时间定一个高得离谱的时薪, 低于时薪的事外包或不做; 退休=不为想象中的明天牺牲今天; 不随收入升级生活方式。 不适用于: 需要享受慢节奏的时刻(休息/家庭时间按定义不是浪费)。 Triggers: 时薪/时间管理/外包/琐事/排队/财务自由/退休/hourly rate/delegate.
screen-detox
当用户刷手机/短视频/社交媒体上瘾、感觉空虚、想戒断多巴胺零食时调用。 核心理念: 所有屏幕活动与更少幸福相关(作者断言无例外); 屏幕=用长期后果换短期快感的多巴胺零食; 用习惯替换五步戒断。 不适用于: 工作需要屏幕的职业场景(区分工作屏幕与消费屏幕)。 Triggers: 刷手机/上瘾/短视频/社交媒体/多巴胺/戒断/屏幕时间/screen time/dopamine/addiction.
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
monkey-mind-meditation
当用户脑子停不下来、焦虑反刍、想学冥想/提升专注力时调用。 核心理念: 内心独白(心猴)是失控程序不是"我"; 用调试模式逐条观察念头, 意识到即失去控制; 冥想=收件箱归零/心灵间歇性禁食。 不适用于: 严重精神疾病急性发作(先就医); 需要立刻处理的实际问题(先做事)。 Triggers: 冥想/焦虑/脑子停不下来/胡思乱想/专注/心猴/monkey mind/meditation/anxiety.
dws
【何时用:仅当用户明确指向钉钉/DingTalk(钉钉文档、钉钉日程等)时使用;泛指做文档/表格/待办/审批默认走本地工具,不要误用钉钉】用 dws CLI 管理钉钉:AI表格/AI搜问(找人首选)/目标管理(Agoal)/组织大脑/日历/通讯录/群聊与机器人消息/待办/审批/考勤/日志(日报周报)/DING消息/钉钉文档/云盘/Markdown文件/AI听记/邮箱/在线电子表格(axls)/知识库/白板/开放平台文档/个人IM与OA事件订阅。用户要求操作上述钉钉产品时使用。.
tmeet-skill
何时用:用户明确要通过命令行操作腾讯会议(tmeet),或 Agent 遇到工具缺失/调用失败/能力不足想反馈平台时。OAuth 登录/登出/状态、会议管理(创建/更新/取消/查询/搜索/受邀者)、录制管理(列表/播放地址/智能纪要/转写/权限申请)、会议报告(参会人/等候室/导出明细/异步任务)、通讯录(仅限会议邀请/呼叫入会前置解析,严禁单独查人)、会中控制(呼叫/踢出/等候室)、问题排查。泛指需求默认走本地工具。.