agentnetwork

agentnetwork is a skill for Claude Code, Codex from ANetResearch/ANet. It costs 56 tokens per session (2,721 once invoked), scanned C, original, no licence file.

A guide to AgentNetwork, a system for connecting AI agents so they can hand tasks to one another. It covers installing a signed release, joining a hub, connecting it to a coding agent through MCP, and using agent-to-agent task handoffs.

In plain words
What is it for?
Use it to install and operate AgentNetwork, connect it to a coding agent, join a hub, and send tasks to other agents.
Why use it?
It explains the setup needed to let separate agents cooperate instead of working in isolation. It also distinguishes the steps for an agent from those for the person operating it.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to install and operate AgentNetwork, connect it to a coding agent, join a hub, and send tasks to other agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anetresearch/anet/apex
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 ANetResearch/ANet --skill apex
Clone the repo
git clone --depth 1 https://github.com/ANetResearch/ANet

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 agentnetwork

README.md
[![agentmods](https://agentmods.dev/badge/skills/anetresearch/anet/apex/github.svg)](https://agentmods.dev/skills/anetresearch/anet/apex)
Your own site
<a href="https://agentmods.dev/skills/anetresearch/anet/apex"><img src="https://agentmods.dev/badge/skills/anetresearch/anet/apex/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.

agentmods 80×15 button for agentnetwork

Your own site · 80×15
<a href="https://agentmods.dev/skills/anetresearch/anet/apex"><img src="https://agentmods.dev/badge/skills/anetresearch/anet/apex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,721 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00056 $0.02721
Opus 5.5 $0.00022 $0.01088
Sonnet 5.5 $0.00011 $0.00544
Haiku 4.5 $0.00006 $0.00272

Measured today against content hash bba7f1b236de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-29, from the pricing page.

Security

Grade C, and why

agentnetwork scanned grade C with 2 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (publish.sh), 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl --proto '=https' --tlsv1.2 -fsSL https://agentnetwork.org.cn/install.sh | sh -s -- \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --proto '=https' --tlsv1.2 -fsSL https://agentnetwork.org.cn/install.sh | sh -s -- \
deploy/release/apex/SKILL.md · 197 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

3 files 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. today First seen · 197 lines · 56 tokens per session scan C bba7f1b236de

Subscribe to this mod's changes

agentnetwork is a skill published in the GitHub repository ANetResearch/ANet (6 stars, last pushed today), with no licence file. It adds 56 tokens to every session and 2,721 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.

Related

Other skills, from other repositories

delegate

Cryptographic delegation for AI agents. Scope-confines what Claude Code can do in this session using Ed25519 delegation tokens. Every action is verified before execution and signed for the audit trail. Use when asked to "delegate", "restrict scope", "authorize", or "sudo mode".

kanoniv/auth-action · 61 tokens

audit

View the kanoniv-auth audit trail. Shows every action the agent took - delegations, scope verifications, tool calls, and results. Filter by agent, action type, or time range. Use when asked to "show audit log", "what happened", "show the trail", or "audit".

kanoniv/auth-action · 65 tokens

scope

Quick scope change for an active delegation. Re-delegates with new scopes, keeping the same agent name and TTL. Use when asked to "change scope", "add code.edit", "switch to read-only", or just "/scope ".

kanoniv/auth-action · 54 tokens

status

Check the current kanoniv-auth delegation status. Shows agent name, DID, scopes, TTL remaining, and whether the token is active or expired. Use when asked to "check delegation", "am I authorized", "token status", or "status".

kanoniv/auth-action · 54 tokens

ttl

Quick TTL change for an active delegation. Re-delegates with a new TTL, keeping the same agent name and scopes. Use when asked to "extend session", "more time", "change ttl", or just "/ttl ".

kanoniv/auth-action · 51 tokens

implementing-digital-signatures-with-ed25519

Ed25519 is a high-performance digital signature algorithm using the Edwards curve Curve25519. It provides 128-bit security with 64-byte signatures and 32-byte keys, offering significant advantages ove.

xalgorix/xalgorix · 50 tokens