agent-link

agent-link is a skill for Claude Code, Codex from Riccardo8888/agent-link. It costs 124 tokens per session (3,284 once invoked), scanned A, original, MIT.

A skill for sending messages between coding agents, such as two Claude Code sessions or a colleague's Codex, through an encrypted shared room.

In plain words
What is it for?
Use it for agent-to-agent collaboration, progress updates, work delegation, and waiting for a colleague's response.
Why use it?
It lets agents coordinate, divide work, hand off tasks, and read replies without exposing the message contents to the system carrying them.

Skill for Claude CodeCodex

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

Good fit Use it for agent-to-agent collaboration, progress updates, work delegation, and waiting for a colleague's response.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/riccardo8888/agent-link/link
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.

Any agent
npx skills add Riccardo8888/agent-link --skill link
Clone the repo
git clone --depth 1 https://github.com/Riccardo8888/agent-link

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 agent-link

README.md
[![agentmods](https://agentmods.dev/badge/skills/riccardo8888/agent-link/link.svg)](https://agentmods.dev/skills/riccardo8888/agent-link/link)
Your own site
<a href="https://agentmods.dev/skills/riccardo8888/agent-link/link"><img src="https://agentmods.dev/badge/skills/riccardo8888/agent-link/link.svg" alt="Measured on agentmods" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,284 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00124 $0.03284
Opus 5 $0.00062 $0.01642
Sonnet 5 $0.00025 $0.00657
Haiku 4.5 $0.00012 $0.00328

Measured 8d ago against content hash 07943116a4f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-link 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.

The scan reads SKILL.md. This mod also ships 22 executable files (__init__.py, cli.py, client.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

link/SKILL.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

An end-to-end encrypted channel between coding agents anywhere on the internet. Messages travel through one private git repo everyone can push to, so there is nothing hosted and no inbound port. The repo can be the one they are already working in. Whatever carries them sees only ciphertext. Every message is logged locally under .conv/.

The one rule that matters

link_send and link_inbox never block. They hand off to a local daemon and return in about a millisecond. Use them freely mid-task — telling the room what you just finished costs nothing.

link_wait does block, up to the timeout you pass. Use it only when you genuinely cannot proceed until someone answers. If you have any other work queued, do that work and call link_inbox afterwards instead.

Never spin on link_wait to "keep checking". Send, get on with your work, and read the inbox when you next pause.

Being woken while you are idle

The notification hook only fires while you are already doing something — a tool call, or the human typing. Between turns nothing of yours runs, so a reply that arrives exactly when you are waiting for it sits unread until somebody types. That is the gap where two agents stop being able to work in parallel.

Close it by leaving this running in the background, as a background task your harness watches, not in the foreground:

agent-link wake --timeout 600

It blocks until a message lands and then exits, which is what re-invokes you. Exit 0 means something arrived and the text is on stdout; exit 1 means the window closed with nothing, and you can start another. It peeks rather than reads, so the hook still delivers the message normally — wake notices, it does not consume.

Start one after you send anything you expect an answer to, and start a fresh one each time it exits. Use link_wait instead only when you truly cannot do anything else until the answer comes.

On a machine running two agents, say which install you mean, because a shell carries no CLAUDE_LINK_HOME and the default one belongs to whichever agent installed first:

Read the full file on GitHub · 308 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 · 308 lines · 124 tokens per session scan A 07943116a4f8

Subscribe to this mod's changes

agent-link is a skill published in the GitHub repository Riccardo8888/agent-link (56 stars, last pushed 17d ago), licensed MIT. It adds 124 tokens to every session and 3,284 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

writing-agent-relay-workflows

Use when building multi-agent workflows with @relayflows/core. Covers conversation vs pipeline coordination, WorkflowBuilder/DAG steps, agents, {{steps.X.output}} chaining, repairable verification gates, evidence-based completion, mandatory Claude-then-Codex fresh-eyes review/fix loops with test hardening, channels…

AgentWorkforce/relay · 92 tokens

choosing-swarm-patterns

Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate…

AgentWorkforce/relay · 76 tokens

relay-80-100-workflow

Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, mandatory sequential Claude-then-Codex fresh-eyes review/fix loops…

AgentWorkforce/relay · 121 tokens

creating-skills

Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimization, and real examples.

AgentWorkforce/relay · 39 tokens

using-agent-relay

Use when you are a registered relay agent (a spawned worker, or a lead that called registeragent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup…

AgentWorkforce/relay · 85 tokens

deploying-to-staging-environment

Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.

AgentWorkforce/relay · 44 tokens