inbox-zero

inbox-zero is a command for Claude Code from lynxbat/inbox-zero-claude. It costs 8 tokens per session (1,259 once invoked), scanned A, original, MIT.

A weekly workflow for sorting and processing email until the inbox is empty or organized. It can set up sorting rules and use Outlook to inspect messages.

In plain words
What is it for?
Use it to classify messages, identify important senders, suggest filing rules, and organize emails into folders.
Why use it?
It provides a repeatable way to handle a large inbox instead of deciding what to do with every email from scratch.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add commands/lynxbat/inbox-zero-claude/inbox-zero
Clone the repo
git clone --depth 1 https://github.com/lynxbat/inbox-zero-claude

Made for: Claude Code.

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 inbox-zero

README.md
[![agentmods](https://agentmods.dev/badge/commands/lynxbat/inbox-zero-claude/inbox-zero.svg)](https://agentmods.dev/commands/lynxbat/inbox-zero-claude/inbox-zero)
Your own site
<a href="https://agentmods.dev/commands/lynxbat/inbox-zero-claude/inbox-zero"><img src="https://agentmods.dev/badge/commands/lynxbat/inbox-zero-claude/inbox-zero.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.01259
Opus 5 $0.00004 $0.00629
Sonnet 5 $0.00002 $0.00252
Haiku 4.5 $0.00001 $0.00126

Measured 5d ago against content hash 0912e5c39156, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

inbox-zero 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 5d 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.

.claude/commands/inbox-zero.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inbox Zero Triage

You are helping me achieve inbox zero through a two-pass triage workflow.

First Run Detection

Before anything else, check if this is a first-time setup:

  1. Check if logs/config/folder-sorting-rules.md exists
  2. If missing or empty → Enter Setup Mode (see below)
  3. If exists → Continue to normal triage workflow

Setup Mode (First Run Only)

If logs/config doesn't exist, guide the user through initial setup:

Step 1: Create Directory Structure

cp -r templates/config logs/config
cp -r templates/people logs/people
cp -r templates/topics logs/topics
cp -r templates/companies logs/companies
cp -r templates/programs logs/programs
mkdir -p attachments

Step 2: Verify Outlook MCP

Test that outlook-mcp is configured:

  • Try fetching 1 email from inbox
  • If it fails, guide user to configure outlook-mcp

Step 3: Analyze Inbox (Optional)

Ask: "Would you like me to analyze your recent emails to suggest personalized rules?"

If yes:

  1. Fetch last 50-100 emails from inbox
  2. Identify patterns:
    • Top senders → Suggest as VIPs or auto-file rules
    • Common domains → Suggest vendor classifications
    • Existing Outlook folders → Incorporate into folder rules
  3. Present findings and let user approve/modify
  4. Update logs/config/ files with personalized rules

If no:

  • User can edit templates manually later

Step 4: Confirm Ready

Say: "Setup complete! Your config is in logs/config/. Run /inbox-zero again to start triaging."

Exit setup mode.


Normal Triage Mode

Context Loading Phase

Before starting triage, load context:

  1. Read all files in logs/config/ for urgency rules and send permissions
  2. Read all files in logs/people/ for sender context
  3. Read all files in logs/companies/ for vendor/firm context
  4. Read all files in logs/programs/ for program context
  5. Read all files in logs/topics/ for topic context

If any logs directory is empty, that's fine - we'll create logs as we go.

Read the full file on GitHub · 172 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. 5d ago First seen · 172 lines · 8 tokens per session scan A 0912e5c39156

Subscribe to this mod's changes

inbox-zero is a command published in the GitHub repository lynxbat/inbox-zero-claude (5 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 1,259 once invoked, about $0.0000 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.