What is wezbridge CLAUDE.md?

Instructions for working on wezbridge, an MCP server that lets coding-agent sessions control and exchange messages with other sessions in WezTerm panes. The document describes the repository, its scope, layout, and current behavior.

Use it when developing or operating wezbridge, including spawning sessions, sending prompts, reading output, discovering sessions, and understanding its current version and repository boundaries.

It gives an agent the project context needed to change or use wezbridge without relying on outdated assumptions about removed components.

wezbridge CLAUDE.md — Instructions file for coding agents by wolverin0: Instructions for working on wezbridge, an MCP server that…

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 instructions/wolverin0/wezbridge/claude-md

Clone the repo

git clone --depth 1 https://github.com/wolverin0/wezbridge

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/wolverin0/wezbridge/claude-md.svg)](https://agentmods.dev/instructions/wolverin0/wezbridge/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wolverin0/wezbridge/claude-md"><img src="https://agentmods.dev/badge/instructions/wolverin0/wezbridge/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,342 This file is loaded in full into every session.

When invoked 4,342 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.04342	$0.04342
Opus 5	$0.02171	$0.02171
Sonnet 5	$0.00868	$0.00868
Haiku 4.5	$0.00434	$0.00434

Measured 3d ago against content hash 16ae1c7437d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wezbridge CLAUDE.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`http://127.0.0.1:4200/` returns 404 — that's intentional. The daemon is headless. Verify it's up with `curl http://127.0.0.1:4200/api/panes`, or from any session call the `bridge_health` MCP tool. It binds loopback only

CLAUDE.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wezbridge (v3.5.0)

Status 2026-07-02 (v3.5.0): focused MCP server, not the abandoned theorchestra orchestrator. Zero npm dependencies. The browser dashboard, the orchestrator-worker pane, the React/Vite v3 build, and the orchestra-goose Tier-2 recipes were removed and preserved at the omniclaude-pre-rollback git tag (commit acd3460). If you're a Claude Code session reading this, you are a regular dev session — there is no orchestrator-worker convention anymore.

v3.5.0 highlights: send_prompt/a2a_send now VERIFY submission (read the input box back, retry enter, return submitted) — the manual follow-up send_key("enter") rule is obsolete on v3.5+ servers. spawn_session starts FRESH sessions by default (continue: true to opt back into --continue), and gains agent: claude|codex|shell + model. read_output gains delta/cursor polling. wait_for_idle/spawn_session no longer block the MCP event loop.

What this repo is

An MCP server that exposes mcp__wezbridge__* tools so any Claude Code or Codex CLI session can spawn, prompt, read, and discover other sessions running in WezTerm panes. The core MCP tools talk to the WezTerm CLI directly — they do NOT require the :4200 daemon. Only auto_handoff calls the daemon (/api/panes/:id/auto-handoff); every other tool works with the daemon down. The :4200 HTTP daemon is a separate headless backend (SSE events, telegram-streamer, session-snapshot crash-restore, grades) — start it with npm run dashboard when you want those. Call bridge_health to see, in one shot, whether wezterm is reachable, the daemon is up, and the snapshot watcher is armed.

Security (v3.4.3): the daemon binds 127.0.0.1 only. To expose it on a LAN set WEZBRIDGE_BIND (e.g. 0.0.0.0) — a WEZBRIDGE_API_TOKEN then becomes mandatory or the daemon refuses to start.

What this repo is NOT

Not a browser dashboard (the v2.3-v3.1 dashboard UI was deprecated 2026-05-03 and removed in v3.2.1; see src/DEPRECATED.md)
Not an autonomous orchestrator (the orchestrator-worker pane / JSON-tick / vault-driven escalation system was reverted 2026-05-03)
Not a hosted multi-agent platform
Not a replacement for Claude Code / Codex / wezterm

Read the full file on GitHub · 243 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.

3d ago First seen · 243 lines · 4,342 tokens per session scan A 16ae1c7437d7

Subscribe to this mod's changes

wezbridge CLAUDE.md is an instructions file published in the GitHub repository wolverin0/wezbridge (1 stars, last pushed 15d ago), licensed MIT. It adds 4,342 tokens to every session, about $0.0217 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents agent-orchestration ai-agents claude-code cli codex developer-tools

kungfu copilot-instructions.md

Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.

kungfu-systems/kungfu · 45 tokens

superset CLAUDE.md

Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

superset-sh/superset · 4 tokens

agents CLAUDE.md

Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.

eloylp/agents · 5,296 tokens

growmos AGENTS.md

Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.

codician-team/growmos · 606 tokens

ideate AGENTS.md

Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.

paultyng/ideate · 641 tokens

omk CLAUDE.md

Claude Code instructions for dmae97/omk, covering claude.md, precedence (read this first), omk runtime map (what you're operating inside), this repo: open-multi-agent-kit / omk monorepo and build / test / check commands.

dmae97/omk · 1,841 tokens

wezbridge CLAUDE.md