ccpeer

ccpeer is a skill for Claude Code, Codex from beyarkay/claude-skills. It costs 103 tokens per session (960 once invoked), scanned A, original, MIT.

A tool for finding other Claude Code sessions running on the same computer and sending messages to them.

In plain words
What is it for?
Use it to see which sessions are active, find your own session name, or ask another session about its work.
Why use it?
It lets sessions share context directly instead of making the user copy and paste information between chats.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/brk/projects/mats.

Good fit Use it to see which sessions are active, find your own session name, or ask another session about its work.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 ccpeer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/beyarkay/claude-skills/ccpeer"><img src="https://agentmods.dev/badge/skills/beyarkay/claude-skills/ccpeer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 960 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 $0.00103 $0.00960
Opus 5 $0.00051 $0.00480
Sonnet 5 $0.00021 $0.00192
Haiku 4.5 $0.00010 $0.00096

Measured 8d ago against content hash 927a2ce64e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ccpeer 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 8d 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.

ccpeer/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ccpeer — talk to the other Claudes on this machine

ccpeer is on PATH. Two things it does:

  1. Discover every Claude Code session running on this machine.
  2. Send a message straight into another session's chat.

The point is to move context between sessions without the user copy-pasting it by hand. If you need something another session knows, ask that session.

Discover

ccpeer list          # who is live, what they are doing, where
ccpeer whoami        # your own peer name — this is how peers address you
ccpeer list --json   # same, scriptable
NAME                       PID  STATUS   PANE    CWD
claims-embodiment         8784  shell    %29     /Users/brk/projects/mats
claude-4f                24389  idle     %54     /Users/brk/.dotfiles/.claude
claude-76 (you)          54493  busy     %56     /Users/brk/.dotfiles/.claude

Names come from the registry Claude Code already keeps at ~/.claude/sessions/<pid>.jsonccpeer invents no bookkeeping of its own. STATUS is that session's live state (idle, busy, shell).

Send

ccpeer send claude-4f "Are you still holding the migration lock on schema.sql?"
ccpeer send 24389 "..."          # pid works too
ccpeer send claude-4f "..." --dry-run   # show what would be injected, send nothing

The message is pasted into that session's prompt and submitted, exactly as if someone typed it. There is no mailbox. A reply is just the peer running ccpeer send back at you, which lands in your chat the same way — so a conversation is only ever the two of you taking turns.

Say who you are and what you want. The peer has none of your context.

Long messages spill to a file

Bodies over 2000 characters are written to /tmp/ccpeer/ and the peer is sent a pointer plus a preview, so a large payload never gets typed into a live prompt:

Long message (8431 chars) — please read it in full at: /tmp/ccpeer/20260716-140233-claude-76-a1b2c3.txt

So sharing a big chunk of context is fine — just send it and let it spill:

Read the full file on GitHub · 87 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. 8d ago First seen · 87 lines · 103 tokens per session scan A 927a2ce64e4c

Subscribe to this mod's changes

ccpeer is a skill published in the GitHub repository beyarkay/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 960 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 2026-08-31.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens