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 blockcell-labs/blockcell --skill bcmailgit clone --depth 1 https://github.com/blockcell-labs/blockcellWrote 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/blockcell-labs/blockcell/bcmail)<a href="https://agentmods.dev/skills/blockcell-labs/blockcell/bcmail"><img src="https://agentmods.dev/badge/skills/blockcell-labs/blockcell/bcmail/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/blockcell-labs/blockcell/bcmail"><img src="https://agentmods.dev/badge/skills/blockcell-labs/blockcell/bcmail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00894 |
| Opus 5.5 | $0.00000 | $0.00358 |
| Sonnet 5.5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
bcmail 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 2mo 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
BCMail
Shared {#shared}
- 适合通过工具
exec执行本地脚本python3 skills/bcmail/bcmail.py来发送邮件、查看收件箱、搜索邮件、统计未读和列出文件夹。 - 这个 skill 依赖环境变量
BCMAIL_EMAIL和BCMAIL_PASSWORD。缺任意一项时，先提示用户设置，再继续执行。 - 脚本会按邮箱域名自动选择服务器，当前支持：
163.com、vip.163.com、126.com、vip.126.com、188.com、vip.188.com、yeah.net、gmail.com、outlook.com、qq.com。 - 绝对不能：
- 编造未执行命令的邮件列表、邮件正文、发送结果或未读数量。
- 回显或泄露
BCMAIL_PASSWORD。 - 在收件人、主题或正文缺失时直接发送邮件。
- 在没有明确邮件 ID 时执行
read。
Prompt {#prompt}
-
工具策略：
- 用
exec调用python3 skills/bcmail/bcmail.py ...。 - 若命令成功且有输出，最终回复必须基于实际输出整理，不能改写成未验证的结论。
- 若脚本提示缺少环境变量或不支持的邮箱域名，直接说明原因，不要臆造替代方案。
- 用
-
按意图执行命令：
- 查看最新邮件：
python3 skills/bcmail/bcmail.py inbox - 查看未读邮件：
python3 skills/bcmail/bcmail.py inbox --unread - 限制数量：
python3 skills/bcmail/bcmail.py inbox --limit 5 - 搜索邮件：
python3 skills/bcmail/bcmail.py search --keyword "关键词" - 读取邮件详情：
python3 skills/bcmail/bcmail.py read --id 123 - 统计未读：
python3 skills/bcmail/bcmail.py unread - 列出文件夹：
python3 skills/bcmail/bcmail.py folders
- 查看最新邮件：
-
发送邮件前置条件：
- 必须确认
to、subject、body已完整。 - 用户要求 HTML 邮件时加
--html。 - 用户提供抄送时加
--cc "[email protected],[email protected]"。 - 用户提供附件时加
--attach file1.pdf file2.png。
- 必须确认
-
发送命令示例：
- 纯文本：
python3 skills/bcmail/bcmail.py send --to "[email protected]" --subject "会议" --body "明天下午两点开会" - HTML：
python3 skills/bcmail/bcmail.py send --to "[email protected]" --subject "日报" --html --body "<h1>日报</h1>" - 含抄送和附件：
python3 skills/bcmail/bcmail.py send --to "[email protected]" --cc "[email protected]" --subject "报告" --attach report.pdf chart.png --body "见附件"
- 纯文本：
-
澄清规则：
- 用户只说“发个邮件”但没给全收件人、主题、正文时，先补齐信息。
- 用户要“读某封邮件”但没给明确邮件 ID 时，先让用户提供邮件 ID。
- 用户要“看邮箱”或“查未读”时，不需要额外确认，直接执行。
Summary {#summary}
- 最终回复保留关键信息：发件人、收件人、主题、时间、未读数量或搜索命中情况。
- 发信结果要明确写“已发送”或“发送失败”，并附上脚本返回的关键信息。
- 不要输出无意义调试信息、环境变量原值或内部实现细节。
What ships with it
2 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.
- 2mo ago First seen · 51 lines · 0 tokens per session scan A 0a3776aa18d1
bcmail is a skill published in the GitHub repository blockcell-labs/blockcell (261 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 894 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.