Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace/plugin install credoWrote 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/commands/marcel-bich/marcel-bich-claude-marketplace/peer-lan)<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/peer-lan"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/peer-lan/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.
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/peer-lan"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/peer-lan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.14454 |
| Opus 5.5 | $0.00009 | $0.05782 |
| Sonnet 5.5 | $0.00004 | $0.02891 |
| Haiku 4.5 | $0.00002 | $0.01445 |
Grade B, and why
peer-lan scanned grade B 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo ufw allow from 192.168.1.42 to any port 48610 proto tcp comment 'credo-peer-lan' How it starts
The opening of the file, as written. The whole thing — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credo LAN Peer Relay
The LAN relay lets Claude Code peer sessions on DIFFERENT machines in the same trusted
network see and message each other (ListAgents / SendMessage) without the Anthropic
cloud. It extends the same-machine peer model: a small daemon on each machine publishes
its local sessions to its configured peers over TCP and mirrors every remote session
into the local sessions/ registry so it shows up as an ordinary peer.
One relay per machine serves ALL Claude Code profiles of that machine. A profile is a
config dir (CLAUDE_CONFIG_DIR, e.g. ~/.claude or ~/.claude-work) with a
sessions/ dir in it; sibling profiles of the same user are found automatically. The
roster lists the sessions of every profile, each with its own profile name, every
remote session is mirrored into each profile's sessions/, and a message reaches a
session in any profile. Trust is always checked in the profile of the target session
(see Trusted peers).
The served profiles are chosen in the setup (Setup flow step 2, default: all found) and
kept in the profiles list of the one machine config. Absent means every profile; a list
means exactly those (the profile that holds the config is always served). profiles shows
and changes the list. A profile that is not served sees no LAN peers and gets no relay
or config of its own.
The relay is a no-op until a config file exists. It is OFF by default. Once the config exists it starts automatically on session start (see Auto-start below), so start/stop here is mostly for manual control.
Setup flow (the agent follows this, interactive sessions only)
The LAN side is OFF until the current network is BOUND (whitelist mandatory, fail-closed). Ask every question below with the Ask tool. In autonomous mode never ask: only report that the relay is disabled and why.
Language: every Ask-tool question, warning and explanation to the user is in the user's language (the language of the conversation); fall back to English if it is unknown or unsure. Commands, config keys and the injected hook lines stay English.
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.
- 12d ago Changed · +17 lines d8c9ef0f4ca7
- 13d ago Changed · +186 lines e2e261e5a8ea
- 15d ago Changed · +244 lines a07d55913065
- 16d ago Changed · +195 lines 8bea3558a012
- 17d ago First seen · 208 lines · 22 tokens per session scan B 3353371b4a42
peer-lan is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (12 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 14,454 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
deps-update
Audit and update dependencies safely.
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.