analyze-thread

analyze-thread is a skill for Claude Code from fatbobman/mail-mcp-bridge. It costs 20 tokens per session (2,098 once invoked), scanned A, original, MIT.

An email-thread analysis that reconstructs a conversation from its messages and attachments. It summarizes the timeline, participants, discussion flow, decisions, and changing files.

In plain words
What is it for?
Use it with an email message ID to review the conversation context, track participant interactions and attachments, identify key decisions, and extract action items.
Why use it?
It removes the need to read a long email chain repeatedly to understand what was decided and what still needs action.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the mail-attachment-analyzer plugin — 3 skills, 3 commands shipped together

Good fit Use it with an email message ID to review the conversation context, track participant interactions and attachments, identify key decisions, and extract action items.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fatbobman/mail-mcp-bridge/analyze-thread
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.

Any agent
npx skills add fatbobman/mail-mcp-bridge --skill analyze-thread
Clone the repo
git clone --depth 1 https://github.com/fatbobman/mail-mcp-bridge

Made for: Claude Code.

Or install mail-attachment-analyzer, the plugin that ships this one along with the rest of its 3 skills, 3 commands.

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 analyze-thread

README.md
[![agentmods](https://agentmods.dev/badge/skills/fatbobman/mail-mcp-bridge/analyze-thread/github.svg)](https://agentmods.dev/skills/fatbobman/mail-mcp-bridge/analyze-thread)
Your own site
<a href="https://agentmods.dev/skills/fatbobman/mail-mcp-bridge/analyze-thread"><img src="https://agentmods.dev/badge/skills/fatbobman/mail-mcp-bridge/analyze-thread/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.

agentmods 80×15 button for analyze-thread

Your own site · 80×15
<a href="https://agentmods.dev/skills/fatbobman/mail-mcp-bridge/analyze-thread"><img src="https://agentmods.dev/badge/skills/fatbobman/mail-mcp-bridge/analyze-thread.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 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 $0.00020 $0.02098
Opus 5 $0.00010 $0.01049
Sonnet 5 $0.00004 $0.00420
Haiku 4.5 $0.00002 $0.00210

Measured 8d ago against content hash 9e97b632ab3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

analyze-thread 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.

plugins/mail-attachment-analyzer/skills/analyze-thread/SKILL.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Email Thread

Comprehensive analysis of an email thread including conversation flow, participant interactions, timeline, key points, and attachment evolution.

When to Use

Use this skill when you need to:

  • Understand complete conversation context
  • Track discussion progression over time
  • Identify key decisions and action items
  • See how attachments evolved through the thread
  • Get overview of multi-email conversations

Triggers:

English:

  • "Analyze this email thread <message-id>"
  • "Show me the conversation <message-id>"
  • "What's the thread about <message-id>"
  • "Thread analysis for <message-id>"
  • "Summarize this thread <message-id>"

Chinese:

  • "分析这个邮件线索 <message-id>"
  • "看看这个对话 <message-id>"
  • "整理一下这个线索 <message-id>"
  • "线索内容总结 <message-id>"
  • "这个讨论的脉络 <message-id>"

Invocation Methods

Method 1: Natural Language (Recommended)

User: Analyze this email thread <[email protected]>
AI: [Proceeds to analyze immediately]

Method 2: Slash Command

User: /analyze-thread
AI: 请提供线索中任意一封邮件的 Message-ID
User: <[email protected]>
AI: [Proceeds to analyze]

Note: Any message-id from the thread works. The system will find all related emails.

Execution Steps

  1. Get message-id (if not provided)

    Please provide any Message-ID from the thread
    
    💡 Quick method (recommended):
    In Mail.app: Select email → Press shortcut (⌘⇧C) → Message-ID copied
    See README "Setup Mail Quick Action" section if not configured
    
  2. Read thread using MCP

    thread_data = mcp__mail__read_thread(message_id)
    
  3. Handle truncation checks

    Check 1: Thread Result Oversized

    • If result indicates size overflow (>80KB):
      • Warn user about thread size
      • Suggest reducing max_body_length
      • Ask if user wants to retry with tighter limits

    Check 2: Individual Email Truncation

    • After successful load, check for truncated emails
    • Classify by importance:
      • ⚠️ Critical: Truncated + has attachments
      • ⚠️ High: Lost 60%+ content
      • ℹ️ Medium: Only quote-stripped
    • Suggest reading important emails individually if needed

Read the full file on GitHub · 313 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 · 313 lines · 20 tokens per session scan A 9e97b632ab3e

Subscribe to this mod's changes

analyze-thread is a skill published in the GitHub repository fatbobman/mail-mcp-bridge (19 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 2,098 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.