agent-mailbox by charanjit-singh: Claude Code mod code

What it does

Draws a band above the prompt, toasts
Adds /mailbox
Watches mcp__agent-mailbox__list_peers, mcp__agent-mailbox__set_label calls
Hooks prompt.submit, session.end, session.measure, session.start and 1 more
Starts processes

Good points

No network calls
Small: 365 lines
Written in TypeScript
Handles errors

Code to start from

A starter ModsCode writes from the drawing it read, and the mod's own lines that draw, where there are any.

Starter (register.tsx)

import type { Register } from 'claude-code'

// Drawn like agent-mailbox by Charanjit Singh (band, toast), as ModsCode read it from the mod's code:
// https://modscode.com/claude-mods/mods/charanjit-singh-agent-mailbox/
// Written by ModsCode from that reading, not copied from the mod: use it as you like.
// Each value below stands for one the mod works out at run time; put in your own.
export const register: Register = on => {
  // the band above the prompt; what else goes there is drawn under it
  on('ui.render', { component: 'AbovePrompt' }, async ($, e, next) => {
    const { Box, Text } = $.ui.resolve(e)
    const name = '…'
    const name2 = '…'
    const peers = '…'
    const more = '…'
    const unread = '…'
    const profile = '…'
    const who = '…'
    const compact = '…'
    const limitLabel = '…'
    const percent = '…'
    const cost = '…'
    return (
      <Box flexDirection="column">
        <Box>
          <Text color="magenta" bold>
            {"✉ "}
            {name}
          </Text>
          <Text dimColor>
            {" · "}
          </Text>
          <Text color="cyan">
            {name2}
          </Text>
          <Text dimColor>
            {" · "}
          </Text>
          <Text>
            {`${peers}${more}`}
          </Text>
          <Text color="yellow">
            {" · "}
            {unread}
            {" new"}
          </Text>
        </Box>
        <Box>
          <Text bold>
            {profile}
          </Text>
          <Text dimColor>
            {" · "}
            {who}
          </Text>
          <Text dimColor>
            {" │ context "}
          </Text>
          <Text>
            ?
          </Text>
          <Text dimColor>
            {" of "}
            {compact}
          </Text>
          <Text>
            {` · ${limitLabel} ${percent}`}
          </Text>
          <Text>
            {` · ${limitLabel} ${percent}`}
          </Text>
          <Text>
            {` · ${limitLabel} ${percent}`}
          </Text>
          <Text dimColor>
            {` · $${cost}`}
          </Text>
        </Box>
        {await next(e)}
      </Box>
    )
  })

  on('session.start', async ($, e, next) => {
    const name = '…'
    const profile = '…'
    const text = '…'
    await $.ui.toast(`✉ ${name} (${profile}): ${text}`)
    return next(e)
  })
}

The mod's own code

Its licence text was not found at the commit read, so only the places in the source are linked.

mod/agent-mailbox/hooks/register.tsx lines 323–364

How to build this: Band above the prompt, Deny a tool call

What its code calls

runs programsreads filesenv varstool calls

What its code shows

Read from the source at commit 3c4a725cd98b on 2026-10-11. The first group decides whether a mod is listed; the rest is for you to weigh. A later commit is not read until the next crawl.

Decides the listing: code you can check
Entry read	Every module hooks/hooks.json names was read.mod/agent-mailbox/hooks/register.tsx
Parses	Every file parses as TypeScript or JavaScript.1 files parsed
All its code is in the mod	Every import is a file of the mod or the engine's own module; no packages, no require.all its code is in the mod
Readable	No minified lines, no eval or new Function, no import of a computed path, no encoded blobs.no minified code, no eval, no encoded blobs
Calls in the open	Network and programs are reached as $.http.fetch and $.process.run in place, never passed around.every call outside goes through $ in the open
For you to weigh before installing
Where it draws	The terminal, the desktop app, both, or nothing (hooks only: a guard or a prompt rewriter), as its code says. Shown, never a reason to leave a mod out.draws in the terminal and the desktop app, the same in both
Install line	Whether its repository's own .claude-plugin/marketplace.json lists it, so it installs from that marketplace with the lines on its page.its repository's .claude-plugin/marketplace.json does not list it: no marketplace line to give; the page shows how to try the commit read
Programs on Windows	Whether every program it starts through $.process exists on Windows (tail, date, open, osascript, /usr/… do not).runs no program a Windows PC lacks
Network	Whether every fetch names its https host in the code.no network
Programs	Whether every program it starts is named in the code and is not a shell, an interpreter or a network tool.mod/agent-mailbox/hooks/register.tsx:46 a program named at run time
Reads and sends	Whether it both reads something of yours (files, environment variables, the transcript, settings) and reaches outside (the network, an MCP server, another session, telemetry).reads environment variables, files, but reaches nothing outside
Keys in the source	Whether the source holds what looks like an API key or a private key.no keys in the source
Licence	An open licence (MIT, Apache-2.0, BSD, ISC, Unlicense, 0BSD, CC0) with its text lets ModsCode show its code; otherwise the code is linked.no licence
Settings hooks	Hooks declared in hooks/hooks.json or plugin.json beside the module: a command (a shell when it has no args), an HTTP request, an MCP tool or a model prompt at an event. They run outside $.no settings hooks: its function hooks alone
Servers it ships	MCP servers (a program, or a URL; a headersHelper is a shell command; a .mcpb bundle is unpacked at run time), LSP servers, monitors (a shell command for the whole session) and bin/ (on the PATH of the Bash tool).ships no MCP or LSP server, no monitor, no bin/
Skills, commands, agents	What its Markdown declares beyond text: allowed-tools granted for the turn, hooks added when a skill is invoked, a command run before Claude reads the skill.no skills, commands, agents or workflows
Tools and MCP	Whether every tool it calls through $.tool.call and $.mcp.call is named in the code, and none is a shell (Bash through the tool runs a shell without $.process).calls no tool, MCP server or command
Asks of the model	Completions it runs ($.model.complete, fork, classify), subagents it spawns, prompts it submits as you, and the tools, commands and agents it adds.adds command mailbox, adds tool list_peers, adds tool send_message, adds tool read_messages, adds tool set_label, adds tool list_mailboxes, adds tool create_mailbox, adds tool select_mailbox, adds tool leave_mailbox
Events it hooks	By what a hook there can do: gates (refuse a tool call, a prompt, a setting, another plugin), shapes (what the model reads: the system prompt, tool descriptions, each request), reads (your input, the events of the settings hooks, every event with *), and the rest.gates: prompt.submit, tool.call (mcp__agent-mailbox__lis…, mcp__agent-mailbox__sen…, mcp__agent-mailbox__rea… (+4)), command.run (mailbox) · also: session.start, turn.complete, session.measure, session.end (+1) · timers: clock.every
Reads, by name	The environment variables and files it names, and whether it reads the transcript, settings.json, the prompt box or the mouse selection.env: HOME, CLAUDE_MAILBOXES_ROOT; files: …/runtime.json, a path computed at run time
Writes, by name	The files and environment variables it names, and whether it changes settings, the prompt box, the clipboard, the conversation (a row the model reads) or another session.writes no files, environment variables, settings or conversation rows

This is a reading of the code text, not a security review: it does not run the mod, and it cannot see what a program the mod starts does. The check before installing is yours. How mods are chosen

Install it

Check it yourself before you install it. Mods run unsandboxed, with your permissions, and ModsCode does not vouch for what this code does. Read its code (or run claude plugin validate . in its folder), weigh what it reaches, and install the commit you read.

Its repository's .claude-plugin/marketplace.json does not list it, so there is no marketplace line to give.

Try the commit ModsCode read

No marketplace needed. In a terminal, clone the repository, check out the commit read, validate the mod, and load it for one session:

git clone https://github.com/charanjit-singh/ClaudeVsCodeMinimal

git -C ClaudeVsCodeMinimal checkout 3c4a725cd98b78e412f17de6609401f73c10ba9d

claude plugin validate ClaudeVsCodeMinimal/mod/agent-mailbox

claude --plugin-dir ClaudeVsCodeMinimal/mod/agent-mailbox

The validate line lists the events the mod hooks and what it asks Claude Code to do, without running it. The last line loads the mod for this session only and writes nothing to your settings. If the author has rewritten history, the commit may no longer exist.

Ask Claude about it

With the ModsCode connector added, Claude can read this mod's code and what it reaches, and build on them. Ask it like this:

Read the ModsCode mod "charanjit-singh-agent-mailbox" with its code and make me one like it

Search them from Claude: the MCP connector

Similar mods

Badge for your README

If this is your mod, paste this into your README. It links to this page.

README.md

[![ModsCode](https://modscode.com/badge/charanjit-singh-agent-mailbox.svg)](https://modscode.com/claude-mods/mods/charanjit-singh-agent-mailbox/)