A secure way to share context between separate Claude Code sessions. The shared information is protected with end-to-end encryption, meaning only the intended sessions can read it.

Use it to pass relevant context between Claude Code sessions while keeping that shared information encrypted.

It helps separate coding sessions work with the same context instead of losing information when switching between them.

backchannel — Plugin for Claude Code by j-ronk

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/j-ronk/backchannel

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/plugins/j-ronk/backchannel/client/github.svg)](https://agentmods.dev/plugins/j-ronk/backchannel/client)

Your own site

<a href="https://agentmods.dev/plugins/j-ronk/backchannel/client"><img src="https://agentmods.dev/badge/plugins/j-ronk/backchannel/client/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/plugins/j-ronk/backchannel/client"><img src="https://agentmods.dev/badge/plugins/j-ronk/backchannel/client.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 7 commands, 2 hooks cost 85 tokens a session between them.

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.

Security

Grade A, and why

backchannel 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 1mo 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.

client/.claude-plugin/plugin.json · 2 lines

What it actually says

{ "name": "backchannel", "version": "0.1.0", "description": "Share context across separate Claude Code sessions (E2E-encrypted)." }

Contents

What it installs

The manifest is a name and a version. 7 commands, 2 hooks travel with it, and installing the plugin installs all of them — 85 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago First seen · 2 lines scan A c7170cab39db

Subscribe to this mod's changes

backchannel is a plugin published in the GitHub repository j-ronk/backchannel (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 Claude Code Collaboration ai-agents aws-cdk claude-code-plugin end-to-end-encryption

devglobe

DevGlobe plugin for Claude Code - appear active on the globe while coding with AI.

Nako0/devglobe-extension · not measured

claude-project-bootstrap

Bootstrap a new repo with working-agreements, GitHub Project, and CLAUDE.md hub-and-spokes — runs github-project-setup, split-claudemd, and bootstrap-working-agreements as one flow or individually.

toBzh30/Claude-Project-Bootstrap · not measured

engineering-craft

Engineering & Claude-coding craft skills (diagnose, tdd, prototype, zoom-out, grill-with-docs, improve-codebase-architecture, to-issues, to-prd) adapted from mattpocock/skills (MIT) to the bootstrap conventions and the AFK/HITL model, plus homegrown skills (checkpoint).

toBzh30/Claude-Project-Bootstrap · not measured

claude-aws-architect

Claude Code plugin for AWS Well-Architected SDLC: design, IaC, cost, security, and observability with grounded citations to AWS docs.

odere-pro/claude-aws-architect · not measured

claude-device-sync

Cross-device session storage, shared memory, and reminders for Claude Code. Sync sessions, memory files, and reminders across multiple devices via an encrypted private Git repository.

hmennen90/claude-device-sync · not measured

han-communication

Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…

testdouble/han · not measured