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/willinvest/claudex/emailnpx skills add WillInvest/ClaudeX --skill emailgit clone --depth 1 https://github.com/WillInvest/ClaudeXWrote 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/willinvest/claudex/email)<a href="https://agentmods.dev/skills/willinvest/claudex/email"><img src="https://agentmods.dev/badge/skills/willinvest/claudex/email.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 | $0.00109 | $0.01832 |
| Opus 5 | $0.00055 | $0.00916 |
| Sonnet 5 | $0.00022 | $0.00366 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
email 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claudex:email — broadcast a brainstorm question to your panel
Send-only. Emails the current question + a short context snapshot to a panel defined in
~/.claude/claudex/panel.json, so people can read it on their own device during a
screen-shared meeting and respond by email or aloud. It does NOT collect, match, or summarize
replies, and does NOT change claudex:think.
Canonical invocation: /claudex:email [filter]. Replies land in the connected Gmail account
and are not monitored live.
Step 1 — Parse panel (true fail-fast)
Read ~/.claude/claudex/panel.json. If it is missing or does not parse, STOP and tell the
host to create/fix it. Recipients are parsed from data.panel.members; the members array is
nested under the top-level panel key. Minimal required shape:
{
"panel": {
"members": [
{ "name": "Name", "email": "[email protected]", "role": "student", "include": true }
]
}
}
If panel.members is missing or is not an array, treat it as a panel schema error and STOP
before drafting. This is the only hard stop before drafting — everything else still produces
a draft you can fall back to.
Step 2 — Resolve recipients
Resolve recipients only from data.panel.members plus any validated ad-hoc email tokens.
- No argument: every member with
include: true. - Argument contains a token with
@: strip surrounding angle brackets, commas, semicolons, and whitespace from each such token; lowercase the domain; then validate it against a conservative email regex such as^[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}$. If any@token is not a valid email, STOP and list the rejected tokens. Valid ad-hoc emails are combined with any other (non-@) filter tokens. - Other tokens (case-insensitive):
professor/professors→role: professor;student/students→role: student.- Name tokens (e.g.
florescu bozdog) match againstname. Multiple tokens are OR —florescu bozdogresolves to BOTH people, not one person matching both.
- NEVER select a member with
include: falseunless explicitly named in the argument. - Each selected member from
panel.membersmust have non-empty stringname,email, androlefields plus a booleanincludefield. If any selected member fails this validation, STOP. If any selected member lacks a valid email, show which selected member is invalid. - Deduplicate the final recipient list by normalized lowercased email before preview, send, and log. Show the unique recipient count.
- If zero recipients resolve, STOP and show what matched / was excluded.
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 · 138 lines · 109 tokens per session scan A 663991bc3650
email is a skill published in the GitHub repository WillInvest/ClaudeX (4 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 1,832 once invoked, about $0.0005 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
brainstorming-research-ideas
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
pdlc-feature
全自动 PDLC 新功能开发(串联 PRD→设计→TDD→实现→评审→发布).
pdlc-quality
Skill "pdlc-quality" from kanfu-panda/pdlc-skills, covering 质量闸门与报告, 这个命令的立身之本, 前置:两份真源, --init:首次建立目标声明 and 段一:跑真实 check.
pdlc-adopt
扫描现有项目结构,逆向生成基线文档,并进行健康检查发现潜在问题。让旧项目平滑接入 PDLC 流程。.
pdlc-review
Skill "pdlc-review" from kanfu-panda/pdlc-skills, covering 代码评审, pdlc 前置检查(必须执行,不可跳过), 评审流程, 评审检查项(逐项检查,发现问题立即修复) and 设计一致性(对照设计文档).
pdlc-test-setup
立测试地基(探测技术栈 → 验证并生成 test-commands.yml → 脚手架测试目录 → 接本地钩子).