agentmailbox-claude-code

A persistent context and messaging setup for Claude Code, a command-line coding agent. It keeps changing session details such as decisions, progress, and open questions on a server, alongside the static project notes in CLAUDE.md.

In plain words
What is it for?
Use it to configure AgentMailbox, start its server, connect Claude Code, and coordinate context between agents or sessions.
Why use it?
It helps work continue across terminal sessions and lets agents share handoff information. This separates lasting project instructions from changing work status.

Skill for Claude CodeCodex

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 skills/ragavrida/agentsmcp/claude-code
Any agent
npx skills add RagavRida/agentsmcp --skill claude-code
Clone the repo
git clone --depth 1 https://github.com/RagavRida/agentsmcp

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 813 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 $0.00070 $0.00813
Opus 5 $0.00035 $0.00407
Sonnet 5 $0.00014 $0.00163
Haiku 4.5 $0.00007 $0.00081

Measured 2d ago against content hash 4179fc7bec3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentmailbox-claude-code 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 2d 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.

skills/claude-code/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentMailbox — Context Sync for Claude Code

Your context follows you across terminal sessions and tools.

AgentMailbox gives Claude Code persistent memory across sessions. Combined with CLAUDE.md for static project context, AgentMailbox provides dynamic, evolving context that tracks decisions, progress, and open questions across every session and every tool.

Setup

1. Add MCP to Claude Code

Add to your Claude Code MCP settings:

{
  "mcpServers": {
    "agentsmcp": {
      "command": "npx",
      "args": ["-y", "agentsmcp-adapter"],
      "env": {
        "AGENTSMCP_AGENT_ID": "claude-code@local",
        "AGENTSMCP_SERVER": "http://localhost:3000"
      }
    }
  }
}

2. Start the Server

npx agentsmcp-server
# Runs at http://localhost:3000

Or use the demo server:

AGENTSMCP_SERVER=https://hdnxa5c8yr.us-east-1.awsapprunner.com

How It Works with CLAUDE.md

Layer Purpose Persistence
CLAUDE.md Static project context (coding standards, architecture, conventions) File-based, manual
AgentMailbox Dynamic session context (decisions, progress, open questions, handoffs) Server-backed, automatic

Use both together:

  • CLAUDE.md for what the project is
  • AgentMailbox for what happened and what's next

Workflows

Session Start

Tool: agentsmcp_receive

Check for context from previous sessions or messages from other agents/tools.

After Terminal Work

Record what you accomplished:

Tool: agentsmcp_send
Arguments:
  to: "claude-code@local"
  body: {
    "session": "Terminal session summary",
    "commands": ["npm test — all passing", "npm run build — clean"],
    "decisions": ["Migrated to ESM modules"],
    "filesChanged": ["package.json", "tsconfig.json", "src/index.ts"],
    "remainingTasks": ["Update CI config for ESM"]
  }

Handoff to GUI Tools

When the user wants to continue in Cursor or Claude Desktop:

Tool: agentsmcp_send
Arguments:
  to: "cursor@local"
  body: {
    "handoff": "ESM migration 80% complete",
    "remainingWork": "Update CI pipeline, fix 2 failing integration tests",
    "context": "See thread for full migration log"
  }

Read the full file on GitHub · 121 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. 2d ago First seen · 121 lines · 70 tokens per session scan A 4179fc7bec3b

Subscribe to this mod's changes

agentmailbox-claude-code is a skill published in the GitHub repository RagavRida/agentsmcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 813 once invoked, about $0.0003 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.