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 Xiaowen-Jiang/agent-enterprise --skill email_triagegit clone --depth 1 https://github.com/Xiaowen-Jiang/agent-enterpriseWrote 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/xiaowen-jiang/agent-enterprise/email_triage)<a href="https://agentmods.dev/skills/xiaowen-jiang/agent-enterprise/email_triage"><img src="https://agentmods.dev/badge/skills/xiaowen-jiang/agent-enterprise/email_triage/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/xiaowen-jiang/agent-enterprise/email_triage"><img src="https://agentmods.dev/badge/skills/xiaowen-jiang/agent-enterprise/email_triage.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 | $0.00019 | $0.00464 |
| Opus 5 | $0.00010 | $0.00232 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
Email Triage 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 10d 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
Process
- Fetch unread emails from the inbox (last 24 hours or as specified)
- Categorize each email into one of four priority levels:
- URGENT: Requires immediate CEO attention (deadlines today, escalations, VIP senders)
- ACTION NEEDED: Requires a response or decision within 1-2 days
- FYI: Informational — no action needed but CEO should be aware
- LOW PRIORITY: Newsletters, automated notifications, non-essential updates
- Summarize each email in 1-2 sentences: sender, subject, key ask or information
- Draft replies for ACTION NEEDED emails when the appropriate response is clear
- Flag patterns: recurring senders, thread counts, topics that keep coming up
Output Format
Present results grouped by priority:
URGENT (N emails)
- From: sender — Subject: subject line Summary: one-line summary of what's needed Suggested action: what the CEO should do
ACTION NEEDED (N emails)
- From: sender — Subject: subject line Summary: one-line summary Draft reply: (if appropriate)
FYI (N emails)
- Brief list with sender and one-line summary
LOW PRIORITY (N emails)
- Brief list, or just a count if many
Guidelines
- Always show URGENT items first
- For draft replies, keep the tone professional but match the CEO's style if known
- If an email thread has multiple messages, summarize the full thread, not just the latest
- Save the triage summary to workspace as
email_triage_YYYY-MM-DD.mdfor reference - Use
save_memoryto remember VIP contacts and recurring patterns - Never send emails without explicit CEO approval — only draft them
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.
- 10d ago First seen · 50 lines · 19 tokens per session scan A 69be9c340582
Email Triage is a skill published in the GitHub repository Xiaowen-Jiang/agent-enterprise (52 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 464 once invoked, about $0.0001 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
gmail
Send, read, and manage Gmail messages and email attachments automatically.
live-tutorial
Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.
novu-design-workflow
Design notification workflows the Novu way — choose channels, set severity, decide when a workflow is critical, configure digests, and route based on subscriber state. Applies to BOTH dashboard-authored and code-first (@novu/framework) workflows. Use when planning a new workflow, deciding which channels to include…
human-cli
Reach the actual human you're working for via the human CLI (ask/approve/choose/tell) when you need a decision, approval, or notification and no one is watching this terminal right now. Use for background/autonomous/scheduled runs, risky or irreversible actions, and genuine multi-way ambiguity — not for routine…
novu-manage-preferences
Configure notification preferences in Novu at the workflow and subscriber level. Set default channel preferences (email, SMS, push, chat, in-app), mark preferences as read-only or subscriber-editable, and manage subscriber-specific overrides. Use when setting up notification opt-in/opt-out, configuring per-channel…
atomicmail
Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.