agentlink-messenger

agentlink-messenger is a skill for Claude Code, Codex from Oryntai/AgentLink. It costs 53 tokens per session (1,013 once invoked), scanned A, original, MIT.

A persistent, encrypted messaging connection between two trusted coding agents. It supports asking questions, sending requests, sharing updates, and checking messages or replies.

In plain words
What is it for?
Use it when another agent can answer a question, perform a separate request, or receive progress updates.
Why use it?
It gives agents a way to coordinate work and exchange information without treating every message as a one-off transcript.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/oryntai/agentlink/agentlink-messenger
Any agent
npx skills add Oryntai/AgentLink --skill agentlink-messenger
Clone the repo
git clone --depth 1 https://github.com/Oryntai/AgentLink

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 agentlink-messenger

README.md
[![agentmods](https://agentmods.dev/badge/skills/oryntai/agentlink/agentlink-messenger.svg)](https://agentmods.dev/skills/oryntai/agentlink/agentlink-messenger)
Your own site
<a href="https://agentmods.dev/skills/oryntai/agentlink/agentlink-messenger"><img src="https://agentmods.dev/badge/skills/oryntai/agentlink/agentlink-messenger.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,013 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00053 $0.01013
Opus 5 $0.00026 $0.00507
Sonnet 5 $0.00011 $0.00203
Haiku 4.5 $0.00005 $0.00101

Measured 3d ago against content hash 2851e662d7d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentlink-messenger 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 3d 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.

skills/agentlink-messenger/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use the AgentLink MCP tools as part of normal collaboration, not as a one-off transcript dump. The peer has no direct access to this machine; every reply remains this agent's judgment.

Routine

  1. At task start, call peer_status, peer_inbox_list, and peer_request_status as appropriate. Repeat after substantial work, after an owner notification, and before the final response. Do not poll tightly.
  2. Answer before asking. Before every peer_ask or peer_request_send, check peer_inbox_list and deal with what is already waiting. When both agents write at the same time the conversations cross and both lose a round; reading first prevents it. Heed the unread-inbound warning these tools return.
  3. Pick the right message type. peer_ask when the answer blocks current work. peer_request_send when local work can continue; retain the request ID and collect it later with peer_request_status. peer_notify for one-way information that needs no reply — progress updates, "the server is up", "wrapping up". Never send an FYI as a request, and never answer a received FYI.
  4. A request you sent stays an obligation on the peer until it is answered. If a later message supersedes it, or you sent it by mistake, withdraw it with peer_cancel — telling the peer in text to "ignore my last message" leaves an unanswered request in its inbox, and it will dutifully answer both. Withdrawal only works until the peer's agent claims it; after that, send a correction instead.
  5. When serving a peer, use peer_listen or claim an item with peer_inbox_claim, inspect only the necessary local resources, then answer with peer_respond. A dedicated responder task is a live service: keep peer_listen pending with timeout_seconds: 86400; after every peer_respond, timeout, FYI, or recoverable error, check the inbox and immediately re-arm peer_listen.
  6. For a multi-step joint plan, negotiate it with peer_goal before using peer_exchange or peer_reply; finish it with peer_complete. Completion does not end the link.
  7. Never leave silently. Before ending your part of a collaboration: answer everything still queued, then propose peer_complete or send a final peer_notify. Keep shared services (dev servers, databases the peer tests against) running until the peer confirms it no longer needs them.

Read the full file on GitHub · 43 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 43 lines · 53 tokens per session scan A 2851e662d7d7

Subscribe to this mod's changes

agentlink-messenger is a skill published in the GitHub repository Oryntai/AgentLink (0 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 1,013 once invoked, about $0.0003 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

agent-link

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"…

Riccardo8888/agent-link · 124 tokens

ironmesh-peers

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.

WizTheAgent/IronMesh · 47 tokens

ironmesh-send

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.

WizTheAgent/IronMesh · 49 tokens

ironmesh-audit

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.

WizTheAgent/IronMesh · 40 tokens

ironmesh-status

Report IronMesh mesh health — uptime, active peer count, message lifetime percentiles, queue pressure. Use when the user asks "is the mesh ok", "how's ironmesh", or before taking actions that depend on a peer being reachable.

WizTheAgent/IronMesh · 53 tokens

ironmesh-trust

Inspect and manage IronMesh's TOFU trust store — list pinned peers, show revocations, revoke a compromised peer. Revoke has side effects and requires the user's explicit confirmation.

WizTheAgent/IronMesh · 41 tokens