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 ericporres/email-triage-plugin --skill email-triagegit clone --depth 1 https://github.com/ericporres/email-triage-pluginWrote 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/ericporres/email-triage-plugin/email-triage)<a href="https://agentmods.dev/skills/ericporres/email-triage-plugin/email-triage"><img src="https://agentmods.dev/badge/skills/ericporres/email-triage-plugin/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/ericporres/email-triage-plugin/email-triage"><img src="https://agentmods.dev/badge/skills/ericporres/email-triage-plugin/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 | $0.00067 | $0.01590 |
| Opus 5 | $0.00034 | $0.00795 |
| Sonnet 5 | $0.00013 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
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 11d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Triage Skill
Overview
Scan Gmail for recent messages, classify them into three priority tiers, and offer to draft replies for urgent items.
Step 0 — Load Context (optional)
If you use a family-assistant skill or maintain reference files with contact and alias data, load them here before scanning. This gives the triage engine context about who matters and which aliases map to which priority.
Example reference files (if available):
| File | What it provides |
|---|---|
family-members.md |
Names, relationships, emails — always Tier 1 |
email-aliases.md |
Alias routing & default priority tiers |
household.md |
Schools, services — helps classify household emails |
Tip: The family-assistant-skill template is a good companion for this plugin. It provides the contact and household context that makes triage smarter.
If you don't have reference files yet, the skill still works — it just classifies based on content and sender patterns instead of alias routing.
Step 1 — Scan Inbox
Use Gmail MCP tools to search:
Query: in:inbox newer_than:1d
Add exclusions for any labels you handle separately (e.g., -label:AI if you have an AI newsletter digest).
Why not is:unread: Many people casually browse emails on their phone without intending to act on them. Read status is unreliable as a triage signal. Use time-based windowing instead.
Time window options:
- Default:
newer_than:1d(last 24 hours — good for daily morning triage) - "Just today":
newer_than:12h - "Catch me up" or "this week":
newer_than:3d
Snippet-first approach: The search results include subjects, senders, and snippets. Classify from these first. Only call read_gmail_message for:
- All Tier 1 emails (need full context for reply drafting)
- Ambiguous Tier 2 emails where the snippet isn't enough to classify
This avoids token blowout on high-volume days.
Step 2 — Classify into Tiers
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.
- 11d ago First seen · 180 lines · 67 tokens per session scan A a6803aee9d76
email-triage is a skill published in the GitHub repository ericporres/email-triage-plugin (27 stars, last pushed 6mo ago), licensed MIT. It adds 67 tokens to every session and 1,590 once invoked, about $0.0003 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
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…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.