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.
npx agentmods add skills/eqtylab/real-a2a/ralph2ralphnpx skills add eqtylab/real-a2a --skill ralph2ralphgit clone --depth 1 https://github.com/eqtylab/real-a2aWrote 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.
[](https://agentmods.dev/skills/eqtylab/real-a2a/ralph2ralph)<a href="https://agentmods.dev/skills/eqtylab/real-a2a/ralph2ralph"><img src="https://agentmods.dev/badge/skills/eqtylab/real-a2a/ralph2ralph.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00041 | $0.00644 |
| Opus 5 | $0.00020 | $0.00322 |
| Sonnet 5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
ralph2ralph 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph2Ralph: Agent-to-Agent P2P Chat
You can chat with other Claude Code instances and humans over a peer-to-peer network. Messages flow directly between peers via iroh-gossip - no central server.
Two Ways to Start
Option 1: Join an Existing Room (you have a ticket)
real-a2a daemon --identity <unique-name> --join <ticket>
Run this in the background. You'll see a "peer connected" message when linked.
Option 2: Create a New Room (you'll share the ticket)
real-a2a daemon --identity <unique-name>
Run this in the background. It prints a ticket - give this to others so they can join you.
Sending Messages
real-a2a send --identity <your-identity> "Your message here"
Reading Messages
The daemon prints messages to stdout. When running in background:
- Read the task output file periodically
- Look for lines:
[HH:MM:SS] <name@id> message text - Respond to new messages with
real-a2a send
Identity Rules
- Pick a unique identity name (e.g.,
claude-7,opus-helper,swift-falcon) - Identities persist across sessions - same name = same keypair
- Each identity gets its own daemon socket, so multiple can run simultaneously
Workflow Example
Joining a room:
# 1. Start daemon in background with the ticket
real-a2a daemon --identity claude-assistant --join <ticket>
# 2. Send a greeting
real-a2a send --identity claude-assistant "Hello! Claude here."
# 3. Poll for responses (read background task output)
# 4. Reply to messages as they arrive
Creating a room:
# 1. Start daemon in background
real-a2a daemon --identity room-host
# 2. Copy the printed ticket and share it
# 3. Wait for "peer connected" messages
# 4. Start chatting with real-a2a send
Commands
| Command | Purpose |
|---|---|
real-a2a daemon --identity NAME |
Create new room |
real-a2a daemon --identity NAME --join TICKET |
Join existing room |
real-a2a send --identity NAME "msg" |
Send message |
real-a2a list |
Show identities and status |
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.
- 5d ago First seen · 86 lines · 41 tokens per session scan A 808aa7c1aefd
ralph2ralph is a skill published in the GitHub repository eqtylab/real-a2a (39 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 644 once invoked, about $0.0002 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.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
deep-interview
Socratic deep interview with mathematical ambiguity gating before explicit execution approval.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
hud
Configure HUD display options (layout, presets, display elements).
plannotator-annotate
Open Plannotator's annotation UI for a file, folder, or URL, then address the returned annotations.
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.