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 UseJunior/email-agent-mcp --skill email-triagegit clone --depth 1 https://github.com/UseJunior/email-agent-mcpWrote 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/usejunior/email-agent-mcp/email-triage)<a href="https://agentmods.dev/skills/usejunior/email-agent-mcp/email-triage"><img src="https://agentmods.dev/badge/skills/usejunior/email-agent-mcp/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/usejunior/email-agent-mcp/email-triage"><img src="https://agentmods.dev/badge/skills/usejunior/email-agent-mcp/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 | $0.00100 | $0.01634 |
| Opus 5 | $0.00050 | $0.00817 |
| Sonnet 5 | $0.00020 | $0.00327 |
| Haiku 4.5 | $0.00010 | $0.00163 |
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 9d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zero-Trust Email Triage
AI is fast enough that if it sees an email, it can respond quickly. The failure mode is not slow response — it is surfacing noise that drowns out real signal. This skill teaches agents to classify email by sender trust, not by arrival order or self-claimed urgency.
The Problem
Most email agents treat all unread email as equally important. This creates two failure modes:
- Noise escalation — a marketing email from an unknown sender with "URGENT" in the subject gets surfaced alongside a client asking for help
- Buried signal — a partner reply sits unread for days because it arrived between 50 GitHub notifications
Both failures damage trust. The fix is sender-based prioritization.
Primary Classifier: Sender Trust Tiers
Classify every email by who sent it, not what it says:
Tier 1 — Paying Customers and Active Clients
Surface immediately. These are relationships where a missed email damages trust and revenue.
Examples: Client asking for a document review, customer reporting a bug, partner requesting a meeting.
Action: Summarize and surface to the user right away. If the email requires a response, flag it as action-needed.
Tier 2 — Engaged Contacts
Surface promptly. These are people the user has active conversations with — not yet paying, but the relationship has momentum.
Examples: Prospect who attended a demo last week, collaborator on an open-source project, investor in active due diligence.
Action: Include in the next triage summary. Don't delay more than one triage cycle.
Tier 3 — Known Colleagues and Team
Surface promptly but don't interrupt for routine messages.
Examples: Internal team updates, contractor status reports, automated reports from known internal systems.
Action: Include in triage summary. Flag only if the message is time-sensitive or requires a decision.
Tier 4 — Newsletters and Automated Notifications
Batch for later. These are legitimate but not time-sensitive.
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.
- 9d ago First seen · 158 lines · 100 tokens per session scan A db3908b41d2e
email-triage is a skill published in the GitHub repository UseJunior/email-agent-mcp (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 1,634 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
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.