agentmods.dev

cross-claude

cross-claude is a skill for Claude Code, Codex from rblank9/cross-claude-mcp. It costs 105 tokens per session (1,205 once invoked), scanned A, original, MIT.

A connector for asking AI systems outside the current Claude Code session for help, including ChatGPT, Claude.ai, Claude Desktop, or an AI on another computer.

In plain words
What is it for?
Use it when you need to send work to a non-Claude-Code AI or to an AI running in someone else's session or on another machine.
Why use it?
It provides a way to reach collaborators that Claude Code's built-in session messaging cannot address.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code.

not rated 17repo 5d ago A scan 105 tokens original MIT

Good fit Use it when you need to send work to a non-Claude-Code AI or to an AI running in someone else's session or on another machine.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rblank9/cross-claude-mcp/skill
View source ↗ rblank9/cross-claude-mcp crosswi.re
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 rblank9/cross-claude-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/rblank9/cross-claude-mcp

Made for: Claude Code, Codex.

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 cross-claude

README.md
[![agentmods](https://agentmods.dev/badge/skills/rblank9/cross-claude-mcp/skill/github.svg)](https://agentmods.dev/skills/rblank9/cross-claude-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/rblank9/cross-claude-mcp/skill"><img src="https://agentmods.dev/badge/skills/rblank9/cross-claude-mcp/skill/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 cross-claude

Your own site · 80×15
<a href="https://agentmods.dev/skills/rblank9/cross-claude-mcp/skill"><img src="https://agentmods.dev/badge/skills/rblank9/cross-claude-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,205 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 $0.00105 $0.01205
Opus 5 $0.00053 $0.00602
Sonnet 5 $0.00021 $0.00241
Haiku 4.5 $0.00011 $0.00120

Measured 9d ago against content hash 9d3bffea7ea8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cross-claude 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 9d 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.

skill/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Claude MCP — external-participant fallback

Scope is now narrow. Use this skill ONLY when the peer is one of:

  1. A non-Claude-Code AI — ChatGPT, Claude.ai (web), Claude Desktop.
  2. An AI on someone else's machine — outside this harness's session registry.

Everything else goes native. SendMessage + ListAgents are built into the harness, are push-delivered, need no registration, no channel, and no polling — and they work better. See the cross-session skill. That includes cases this skill used to own:

  • Another Claude Code session → SendMessage, addressed by project-dir basename.
  • Spawning a peer in another project → cd <project-dir> && claude --bg "<task>". It inherits that project's CLAUDE.md, memory, MCP servers, skills, and hooks — the whole reason spawn-collaborator existed. Verified end-to-end 2026-08-21. Do not use spawn-collaborator for this; it is superseded.
  • The MANDATORY cross-project change rule → lives in cross-session now. Read it there.

If you are reaching for this skill and the peer is a Claude Code session, you are in the wrong skill.

Before Starting (MANDATORY)

If the user's request does not specify a channel, stop and ask: "Which channel should I use?" Do not call any Cross-Claude tools until a channel is provided.

Once a channel is specified:

  1. register with a descriptive instance_id (e.g., "builder", "reviewer")
  2. Use that channel — create it if it doesn't exist
  3. Proceed with the user's request

Message Protocol

  • After sending a request, call wait_for_reply immediately — don't wait for user prompt
  • Stop polling only when: you receive a done message, or the user says "disconnect"/"stop listening"
  • For large data (>500 chars), use share_data then reference the key in the message
  • Use typed messages: request, response, handoff, status, done
  • Keep your instance_id consistent — don't re-register mid-conversation
  • When you poll, prefer the after_id from your last read (the "Last message ID" line of a check_messages/wait_for_reply result), not the id send_message just returned for your own message. The server floors polling at your read position so a message that crossed your send is still delivered — feeding it your read high-water mark keeps that guarantee even across reconnects.
  • One wait per channel: starting a new wait_for_reply on a channel you're already waiting on supersedes the old one. Never stack waits.

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 105 tokens per session scan A 9d3bffea7ea8

Subscribe to this mod's changes

cross-claude is a skill published in the GitHub repository rblank9/cross-claude-mcp (17 stars, last pushed 5d ago), licensed MIT. It adds 105 tokens to every session and 1,205 once invoked, about $0.0005 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 2026-08-30.

Building agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens