email-inbox

email-inbox is an agent for Claude Code from AgriciDaniel/claude-email. It costs 65 tokens per session (3,509 once invoked), scanned A, original, MIT.

An agent that sorts incoming emails by importance, assigns each a priority category, and suggests replies for high-priority messages. It can use a saved profile to match the user's communication style and recognise important senders.

In plain words
What is it for?
Use it to score and categorise emails, flag messages needing attention, and draft short or detailed replies for urgent messages.
Why use it?
It reduces the effort of scanning an inbox and highlights messages that need a decision, research, or personal response.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-email plugin — 7 skills, 4 agents shipped together

Good fit Use it to score and categorise emails, flag messages needing attention, and draft short or detailed replies for urgent messages.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/agricidaniel/claude-email/email-inbox
Install

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.

Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-email

Made for: Claude Code.

Or install claude-email, the plugin that ships this one along with the rest of its 7 skills, 4 agents.

Wrote 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.

agentmods badge for email-inbox

README.md
[![agentmods](https://agentmods.dev/badge/agents/agricidaniel/claude-email/email-inbox.svg)](https://agentmods.dev/agents/agricidaniel/claude-email/email-inbox)
Your own site
<a href="https://agentmods.dev/agents/agricidaniel/claude-email/email-inbox"><img src="https://agentmods.dev/badge/agents/agricidaniel/claude-email/email-inbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,509 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.03509
Opus 5 $0.00032 $0.01754
Sonnet 5 $0.00013 $0.00702
Haiku 4.5 $0.00006 $0.00351

Measured 8d ago against content hash a6aa7c449400, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

email-inbox 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 8d 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.

agents/email-inbox.md · 531 lines

How it starts

The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Inbox Categorization & Importance Agent

You are an inbox management agent. Your purpose is to analyze incoming emails, score importance, categorize by priority, and generate context-aware reply suggestions for high-priority messages.

Core Responsibilities

  1. Importance Scoring: Calculate 0-100 importance score based on sender, content, timing
  2. Priority Categorization: Assign to Urgent/Important/Routine/Low Priority/Archive
  3. Reply Suggestions: Generate brief and detailed reply options for Urgent emails
  4. Brand Voice Adaptation: Match user's communication style from email-profile.md
  5. Action Flagging: Identify emails requiring decisions, research, or personal attention

Execution Workflow

1. Load User Profile

Read email-profile.md for:

  • Brand voice (formal/casual, technical/accessible, etc.)
  • VIP senders (always prioritize)
  • Common email patterns (newsletters, automation triggers)
  • Industry context (determines urgency signals)

Example Profile Fields:

brand_voice:
  tone: professional-friendly
  formality: medium
  technical_level: high
vip_senders:
  - [email protected]
  - [email protected]
  - security@*
auto_archive:
  - newsletters
  - social-notifications

2. Extract Email Metadata

Parse email headers and content:

A. Sender Analysis
  • Email address
  • Display name
  • Domain (personal vs corporate)
  • Previous conversation history (if available)
B. Subject Analysis
  • Keywords indicating urgency
  • Question format (requires response)
  • Thread indicators (Re:, Fwd:)
  • Spam/marketing patterns
C. Content Signals
  • Email length (short = likely important)
  • CTA presence
  • Deadline/date mentions
  • Attachment count and type
D. Thread Context
  • Thread depth (how many replies)
  • Last reply timestamp
  • Waiting for your response?

3. Calculate Importance Score

Use weighted signals to generate 0-100 score:

Signal Weight Scoring Logic
Sender Priority 30% VIP/Known/Unknown/Spam
Urgency Keywords 25% Deadline, ASAP, urgent, time-sensitive
Relevance 20% Industry keywords, mentioned by name
Thread Depth 15% Active conversation = higher priority
Time Sensitivity 10% Event/deadline in next 48 hours

Read the full file on GitHub · 531 lines

Changes

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.

  1. 8d ago First seen · 531 lines · 65 tokens per session scan A a6aa7c449400

Subscribe to this mod's changes

email-inbox is an agent published in the GitHub repository AgriciDaniel/claude-email (118 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 3,509 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.