A command for reading messages sent directly to your coding session or broadcast to the whole project. It can show unread messages or recent message history.

Use it to read collaboration updates, inspect message history, preview messages without marking them read, or focus on warnings and urgent notices.

It gathers updates from other sessions in one place and lets you filter messages by urgency without checking manually elsewhere.

inbox — Command for Claude Code by garniergeorges

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/garniergeorges/claude-presence

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/garniergeorges/claude-presence/inbox.svg)](https://agentmods.dev/commands/garniergeorges/claude-presence/inbox)

Your own site

<a href="https://agentmods.dev/commands/garniergeorges/claude-presence/inbox"><img src="https://agentmods.dev/badge/commands/garniergeorges/claude-presence/inbox.svg" alt="Measured on agentmods" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 408 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00408
Opus 5	$0.00007	$0.00204
Sonnet 5	$0.00003	$0.00082
Haiku 4.5	$0.00001	$0.00041

Measured 8d ago against content hash eaea922460b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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.

commands/inbox.md · 30 lines

What it actually says

Call the claude-presence MCP read_inbox tool.

Parse $ARGUMENTS:

If it contains all, call with unread_only: false to show the full history (last 50 messages).
Otherwise (or with unread), call with unread_only: true.
If it contains --peek, pass peek: true so the messages stay marked as unread.
If it contains --min-priority <info|warning|urgent>, pass min_priority.

Required args:

session_id: this session's id (from session_register). If unknown, ask the user to /register first.
project: the project's absolute path.

Present each message as:

[time ago] [priority] from <session> (branch) → <target>: message

Where <target> is either me (direct message addressed to this session, i.e. to_session = my session_id) or all (project-wide broadcast). Hide the [priority] bracket when priority is info.

If a message has tags, prepend them in brackets after priority.

If there are no messages, say so plainly (No new messages for unread, No messages yet for all).

The tool response includes unread_total (count at the moment of the call, before mark-as-read) and total (count of all visible messages on this project). Surface both, e.g. "3 new, 12 total" — especially when the user re-runs /inbox rapidly and wonders if they missed something.

Unless --peek was passed, returned messages are auto-marked as read by the tool. Don't warn, just show them.

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.

8d ago First seen · 30 lines · 0 tokens per session scan A eaea922460b1

Subscribe to this mod's changes

inbox is a command published in the GitHub repository garniergeorges/claude-presence (12 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 408 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.

Claude Code cli coordination developer-tools mcp model-context-protocol

inbox

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

optimize

review

test

fix

constitution

plan