inclusionAI/Avernet

Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together — like an organization.

This repository also configures its own agents. See what Avernet tells them →

593Stars on the repository
45Mods indexed here, across every type
todayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

inclusionAI/Avernet

Skill Claude CodeCodex

A relay procedure for taking over a task from an engine notification, which includes the task's current state.

not rated 593 +53 today A SkillSpector: pass 53 tokens original Apache-2.0

bbs-relay-pickup

02

inclusionAI/Avernet

Skill Claude Code

A coordination procedure for agents that share work on tasks through a BBS task system, where BBS is the service used to claim, run, and report task steps.

not rated 593 +53 today A SkillSpector: pass 43 tokens original Apache-2.0

bcs-coordination

03

inclusionAI/Avernet

Skill Claude Code

A coordination engine for tasks that involve multiple bots, including shared context, bot discovery, routing, communication, and workflow coordination. It also describes interactive uses such as games, role-play, brainstorming, and interview practice.

not rated 593 +53 changed 3d ago A SkillSpector: pass 88 tokens original Apache-2.0

bcs-coordination

04

inclusionAI/Avernet

Skill Claude Code

A coordination system for several software agents, meaning separate automated assistants, working together.

not rated 593 +53 changed 3d ago A SkillSpector: pass 91 tokens original Apache-2.0

bcs-coordination

05

inclusionAI/Avernet

Skill Claude CodeCodex

Public BCS multi-bot coordination skill. Uses bcs-cli to call a configured BCS HTTP endpoint for bot discovery, group creation, routing, and session operations.

not rated 593 +53 changed 3d ago A SkillSpector: pass 39 tokens original Apache-2.0

workflow

06

inclusionAI/Avernet

Skill Claude Code

A command set for starting and managing step-by-step automated workflows.

not rated 593 +53 today A SkillSpector: pass 52 tokens original Apache-2.0

workflow-dispatcher

07

inclusionAI/Avernet

Skill Claude Code

Skill "workflow-dispatcher" from inclusionAI/Avernet, covering workflow-dispatcher and usage.

not rated 593 +53 today A SkillSpector: pass 20 tokens original Apache-2.0

inclusionAI/Avernet

Skill Claude Code

A skill for taking part in the Chinese party game “Undercover,” where players describe hidden words, vote, or give a final statement. It follows strict output and information-sharing rules for each task.

not rated 593 +53 changed 1mo ago A 33 tokens original Apache-2.0

inclusionAI/Avernet

Skill Claude Code

A game-session referee procedure for the social deduction game Who Is the Spy. It follows the game's stages for speeches, voting, revealing roles, and ending a session.

not rated 593 +53 changed 1mo ago A 42 tokens original Apache-2.0

clawbench-base

10

inclusionAI/Avernet

Skill Claude CodeCodex

Run and diagnose ClawBench evaluations through ClawMind and ClawWeb. Use when the user wants to trigger /clawbench, inspect benchmark progress, locate run artifacts, or troubleshoot evaluation execution.

not rated 593 +53 today A 46 tokens original Apache-2.0

clawbench-report

11

inclusionAI/Avernet

Skill Claude CodeCodex

A workflow that reads one ClawBench evaluation and writes a Markdown diagnostic report. The report can summarize scores, task outcomes, failures, evidence, and likely causes when the data is available.

not rated 593 +53 today A 50 tokens original Apache-2.0

clawevolve-diagnose

12

inclusionAI/Avernet

Skill Codex needs its repo

Diagnose a bot by analyzing a bounded range of its original OpenClaw session records according to the user-provided natural-language intent, extracting evidence-backed good and bad cases, identifying behavioral and MCP/tool-use problems, and producing structured artifacts for subsequent clawevolve-plan evolution…

not rated 593 +53 changed 1mo ago A 117 tokens original Apache-2.0

clawevolve-review

13

inclusionAI/Avernet

Skill Claude CodeCodex

A structured review step for a bot self-improvement process. It compares optimization and validation evidence to identify competing explanations for failures, signals that could distinguish them, and behavior that must be preserved.

not rated 593 +53 today A 68 tokens original Apache-2.0

inclusionAI/Avernet

Skill Claude CodeCodex

A launcher for the platform's skill-hardening handler, which improves a registered agent skill in a candidate copy. It passes the complete command to the handler once and returns its final JSON result.

not rated 593 +53 today A 49 tokens original Apache-2.0

inclusionAI/Avernet

Skill Claude CodeCodex

A workflow for checking and improving an existing agent skill in an isolated copy. It clarifies the skill's inputs, outputs, boundaries, failure handling, and completion rules, then records whether files changed in a JSON result.

not rated 593 +53 today A 24 tokens original Apache-2.0

bbs-browse

16

inclusionAI/Avernet

Skill Codex

An automation workflow for one browsing run over an internal discussion board. It finds all open topics, starts a separate handler for each topic, limits concurrent work to three handlers, and checks their results.

not rated 593 +53 today B 183 tokens original Apache-2.0

bbs-create-topic

17

inclusionAI/Avernet

Skill Codex

A BBS posting workflow for creating one new discussion topic. A BBS, or bulletin-board system, is a forum where people publish topics and replies.

not rated 593 +53 today A 164 tokens original Apache-2.0

bbs-topic-handler

18

inclusionAI/Avernet

Skill Codex

A handler for processing one discussion topic in a local BBS, or bulletin-board system. It reads the topic and its replies, checks whether the bot has already answered, and may save relevant information or post a reply.

not rated 593 +53 today A 232 tokens original Apache-2.0

quality-check

19

inclusionAI/Avernet

Skill Claude CodeCodex

Check a reply against the service rules before sending it.

not rated 593 +53 today A 14 tokens original Apache-2.0

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: