What is agent-bridge-mcp CLAUDE.md?

Instructions for Mevoric, a system that combines shared agent memory with messaging between agents. It documents 12 tools, three automatic hooks, setup, and the local and server parts it uses.

Initializing Mevoric, retrieving or storing memories, registering agents, exchanging messages, sharing context, and saving or loading checkpoints.

It explains how to configure the agent bridge and connect it to the shared memory and messaging services.

How Lloydm15/agent-bridge-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Lloydm15/agent-bridge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Lloydm15/agent-bridge-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Lloydm15/agent-bridge-mcp

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/instructions/lloydm15/agent-bridge-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lloydm15/agent-bridge-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lloydm15/agent-bridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lloydm15/agent-bridge-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lloydm15/agent-bridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lloydm15/agent-bridge-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 612 This file is loaded in full into every session.

When invoked 612 The same file — it is already loaded in full.

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	$0.00612	$0.00612
Opus 5.5	$0.00245	$0.00245
Sonnet 5.5	$0.00122	$0.00122
Haiku 4.5	$0.00061	$0.00061

Measured 2mo ago against content hash c5923d1d04f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-bridge-mcp CLAUDE.md 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 2mo 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.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mevoric

Unified Memory + Agent Bridge. Replaced 3 separate systems (newcode-memory, agent-bridge, Python hooks) with ONE npm package.

Tools (12)

retrieve_memories, store_conversation, judge_memories, register_agent, list_agents, send_message, read_messages, broadcast, share_context, get_context, save_checkpoint, load_checkpoint

Hooks (3)

--bootstrap-context (SessionStart)
--capture-prompt + --check-messages (UserPromptSubmit)
--ingest (Stop)

Setup

npx mevoric init --server http://192.168.2.100:3100 — handles global config, project configs, hooks, permissions, legacy pip cleanup

How It Runs

Hub runs on the Linux server (192.168.2.100:4100) via pm2 as mevoric-hub
- Start: ssh to server → pm2 start hub.mjs --name mevoric-hub
- Auto-restarts on crash and on server reboot (pm2 saved)
MCP client (server.mjs) runs locally on Lloyd's PC via Claude Code's MCP config
- Path: C:/dev/mcp-tools/mevoric/server.mjs
- Memory server: http://192.168.2.100:3100 (Cortex — /api/retrieve works, /api/ingest currently returns {"status":"skipped","reason":"mevoric-ingest disabled to reduce memory bloat"})
- Hub (legacy): http://192.168.2.100:4100 — the MCP client still points here via env var, but the runner now talks to Cortex council on :3100/api/council/*
- Data dir: C:\Users\lloyd\AppData\Local\agent-bridge

Infrastructure

Memory server: 192.168.2.100:3100 (Cortex API — /ingest, /retrieve, /feedback endpoints). Mevoric is just the client.
Hub: 192.168.2.100:4100 (pm2: mevoric-hub, handles agent messaging + knowledge sharing)
Data dir: C:\Users\lloyd\AppData\Local\agent-bridge (legacy path preserved)
Tests: cd c:\dev\mcp-tools\mevoric && node --test test/stress.test.mjs (50 stress tests)
Runner: start-runner.bat is registered as a Windows scheduled task ("Mevoric Runner", auto-start at logon) — runs runner.mjs which polls Cortex council every 10s and wakes Claude CLI for direct messages

Read the full file on GitHub · 32 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.

2mo ago First seen · 32 lines · 612 tokens per session scan A c5923d1d04f4

Subscribe to this mod's changes

agent-bridge-mcp CLAUDE.md is an instructions file published in the GitHub repository Lloydm15/agent-bridge-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

Building agents Memory and context

agent-bridge-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-bridge-mcp CLAUDE.mdLloydm15/agent-bridge-mcp	Instructions file	0	4mo ago	MIT	A	612	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-bridge-mcp: Instructions file for Claude Code