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.
git clone --depth 1 https://github.com/fatbobman/mail-mcp-bridgeWrote 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/commands/fatbobman/mail-mcp-bridge/analyze-thread)<a href="https://agentmods.dev/commands/fatbobman/mail-mcp-bridge/analyze-thread"><img src="https://agentmods.dev/badge/commands/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.
<a href="https://agentmods.dev/commands/fatbobman/mail-mcp-bridge/analyze-thread"><img src="https://agentmods.dev/badge/commands/fatbobman/mail-mcp-bridge/analyze-thread.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 | $0.00000 | $0.00206 |
| Opus 5.5 | $0.00000 | $0.00082 |
| Sonnet 5.5 | $0.00000 | $0.00041 |
| Haiku 4.5 | $0.00000 | $0.00021 |
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 1mo 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
Analyze Email Thread
Comprehensive analysis of an email thread including conversation flow, timeline, participants, and key points.
Use when: You need to understand complete conversation context or track discussion progression.
What it does:
- Reads all emails in the thread
- Shows conversation timeline
- Identifies participants and their roles
- Extracts key decisions and action items
- Tracks attachment evolution
- Handles large threads intelligently
Features:
- Smart quote stripping reduces token usage by ~80%
- Detects and warns about truncated emails
- Suggests reading important emails individually if needed
Example:
User: /analyze-thread
AI: Please provide any Message-ID from the thread
User: <[email protected]>
AI: [Shows full thread analysis with timeline and key points]
Related commands:
/analyze-email- For single email analysis/analyze-attachments- For deep attachment analysis
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.
- 1mo ago First seen · 39 lines · 0 tokens per session scan A 100fdf409a4a
analyze-thread is a command published in the GitHub repository fatbobman/mail-mcp-bridge (19 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 206 tokens. 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 commands, from other repositories
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-export
Export instincts for sharing with teammates or other projects.
continue
Resume incomplete work from continuation tasks, or find the highest-impact next action.
start-11-3.en
Lesson 11-3: News Fetching → Email/Slack Distribution!
start-11-3
A lesson on building a workflow that fetches news from an RSS feed and distributes it by email or Slack. An RSS feed is a regularly updated list of items from a website.
aic-skills
Show all available AIContext skills grouped by workflow stage.