agentmods.dev

agent-bridge

agent-bridge is a skill for Claude Code from southlab-ai/Claude-Plugin-Marketplace. It costs 66 tokens per session (719 once invoked), scanned A, original, MIT.

A bridge between two separate Codex or Claude chats that lets them exchange requests and replies while both chats stay active.

In plain words
What is it for?
Use it to delegate work between chats, wait for another agent's response, or coordinate separate sessions working on the same project.
Why use it?
It avoids copying messages between independent chats or repeatedly checking whether another chat has answered.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Codex.

Part of the agent-bridge plugin — 1 skill, 1 MCP server shipped together

not rated 2repo 1mo ago A scan 66 tokens original MIT

Good fit Use it to delegate work between chats, wait for another agent's response, or coordinate separate sessions working on the same project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/southlab-ai/claude-plugin-marketplace/agent-bridge
View source ↗ southlab-ai/Claude-Plugin-Marketplace
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.

Any agent
npx skills add southlab-ai/Claude-Plugin-Marketplace --skill agent-bridge
Clone the repo
git clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-Marketplace

Made for: Claude Code.

Or install agent-bridge, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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.

agentmods badge for agent-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/agent-bridge/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/agent-bridge)
Your own site
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/agent-bridge"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/agent-bridge/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.

agentmods 80×15 button for agent-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/agent-bridge"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/agent-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00719
Opus 5 $0.00033 $0.00360
Sonnet 5 $0.00013 $0.00144
Haiku 4.5 $0.00007 $0.00072

Measured 11d ago against content hash 3b6c3ab9f2a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-bridge 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 11d 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.

plugins/agent-bridge/skills/agent-bridge/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Bridge

Coordinate independent chats while keeping each chat's current turn open. The sender uses ask and resumes when the receiver calls reply; do not replace this with polling or a new user turn.

Shared identifiers

Before using the bridge, determine:

  • project_key: a stable shared scope agreed by both chats, such as the repository name or a user-provided collaboration name.
  • agent_name: a unique short identity for this chat, such as architect or reviewer.

Names use letters, digits, _, and -. Keep the same identifiers throughout the collaboration.

Register

Call register_agent once at the beginning of the chat's active bridge turn. Include a short description so peers can distinguish roles. If the other peer is not registered yet, report that fact and wait for the user to start it; do not invent another identity.

Receive and remain available

When the user asks this chat to receive work:

  1. Register the identity.
  2. Call listen with a long timeout, normally 3600 seconds.
  3. When it returns a request, preserve request_id exactly.
  4. Complete the requested analysis or work using the chat's normal Codex capabilities.
  5. Call reply with the result and exact request_id.
  6. If the user requested persistent availability, call listen again in the same turn.

An idle result means no request arrived before the timeout. Explain it briefly; do not claim that the peer answered.

Ask and wait synchronously

When the user asks this chat to consult another chat:

  1. Register the identity if needed.
  2. Optionally call bridge_status to verify the target name.
  3. Call ask with the full, self-contained request and a suitable timeout.
  4. Remain in the same turn while the tool is pending. Do not poll, schedule a task, or ask the user to copy messages.
  5. When ask returns replied, treat response as the peer's answer and continue the task.

If ask returns expired or cancelled, state that no usable peer response arrived. Do not fabricate one.

Read the full file on GitHub · 82 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. 11d ago First seen · 82 lines · 66 tokens per session scan A 3b6c3ab9f2a1

Subscribe to this mod's changes

agent-bridge is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 719 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.

Building agentsClaude CodeMulti-Agentai-agentscomputer-visionmarketplacemcp
Related

Other skills, from other repositories

cosmergon

Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against a standing population of always-on agents. Invite other agents for energy rewards. Auto-registers — no API key needed.

rkocosmergon/cosmergon-agent · 50 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens