Talk to other coding agents — another Claude Code, or a colleague's Codex — over an encrypted room. Use when the user wants to coordinate, split, hand off or divide work with another agent; asks what the other agent is doing; says "chiedi al collega", "dillo all'altro Claude", "dividiamoci il lavoro", "pair with"…
Tail the tamper-evident IronMesh audit log for security events. Use when investigating a TOFU mismatch, auth failure, peer dropping out, or a suspected attack.
Drill into per-peer IronMesh metrics — retry reasons, session rekeys, offline-since, transport type. Use when ironmesh-status shows a problem on a specific peer and you need detail.
Send an application message (MSG) to a specific IronMesh peer. Use when the user asks to "send X to agent Y" or "ping peer Z". Has side effects — only invoke when the user explicitly asks.
Manage a backchannel room. Start, join, check status, set the share policy, or leave a shared, E2E-encrypted session with another AI coding session. Use when the user asks to start, join, check, or leave a backchannel, or to share context with a teammate's session.
Set and manage cross-device reminders for Claude Code. Use when the user wants to create a reminder, check pending reminders, or manage the reminder daemon.
Initialize device-sync for cross-device session and memory synchronization. Use when the user wants to set up device sync, connect a sync repository, or configure encrypted cross-device syncing.
Sync Claude Code sessions and memory across devices. Use when the user wants to push or pull sessions, sync memory files, or manage cross-device synchronization.
Adversarial fresh-context review of any non-trivial technical decision or code change. MUST be used before committing any change to smart contract code (xete-tab, Xete Swap), key handling (Black Knight), encryption logic (Xete Message, MCP server), or any irreversible/immutable deployment decision. Also trigger when…
Train and calibrate the gate system against a repo's real git history in an isolated sandbox. MUST be used when the user asks to backtest, replay, calibrate, or train the gates against history, and after installing gates into any repo with meaningful existing history. Uses real historical fixes as ground truth and…
Spec-first workflow for any feature or change expected to exceed one atomic commit, and for all work handed between Chef, Jo, or agent sessions. MUST be used when starting a new feature, refactor, or integration (House Elf features, MCP server changes, relay work, x402 extensions) — write the spec BEFORE any code.…
Operate AgentLink as a persistent, encrypted two-agent messenger. Use whenever AgentLink MCP tools are available, a peer agent is connected, or the task could benefit from asking, answering, or coordinating with a trusted peer agent through AgentLink.
Collaborate live with another person's Claude Code over a shared, end-to-end-encrypted Pairwave channel. Use when two people work on the same project and need to exchange context, code, decisions, or action requests without copy-pasting between their AIs. Invoke as /pairwave. Handles SAS verification, charter…
★not rated 0 2mo agoA94 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: