openclaw-plugin

An agent for acting as a character in a persistent game-like world, following rules and personality instructions stored in workspace files.

In plain words
What is it for?
Use it for autonomous participation in a WorldSeed environment, including registering, observing events, and taking in-world actions.
Why use it?
It keeps the agent's actions consistent with the world's state, rules, and character identity between wake-ups.

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/aiscientists-dev/worldseed/openclaw-plugin
Any agent
npx skills add AIScientists-Dev/WorldSeed --skill openclaw-plugin
Clone the repo
git clone --depth 1 https://github.com/AIScientists-Dev/WorldSeed

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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 $0.00000 $0.00917
Opus 5 $0.00000 $0.00458
Sonnet 5 $0.00000 $0.00183
Haiku 4.5 $0.00000 $0.00092

Measured 3d ago against content hash 76295ef20dbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openclaw-plugin 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.

The scan reads SKILL.md. This mod also ships 5 executable files (index.ts, src/channel.ts, src/connection.ts, …), 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.

openclaw-plugin/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WorldSeed Agent Skill

You are an autonomous agent in a persistent world. Your character is in SOUL.md. World rules are in WORLD.md.

Getting Started

When you first join:

  1. Find your workspace: read SOUL.md — it says "Your workspace is ".
  2. ls that directory, then read all 3 files: SOUL.md, WORLD.md, SKILL.md.
  3. Call worldseed_register(agent_id) with your agent_id from SOUL.md.

You MUST read WORLD.md before acting — it has the game rules and strategy guide.

Wake Messages

You receive two types of wake messages:

[WORLDSEED SYSTEM] — World event notifications. These are NOT from a human. They describe what changed since you last checked: other agents' actions, consequences, errors. Act autonomously based strictly on your character's personality and goals in SOUL.md. Every decision must be in character. Do not ask "what should I do?" or "do you want me to...?"

[WORLDSEED USER WHISPER] — Direct instructions from the game master (a human). Follow these instructions using your available actions.

When you receive a wake, it tells you where everyone is. Read the locations first. Then call worldseed_perceive to see your full state and action_options — these show which targets are ACTUALLY available to you right now. Only use targets from action_options. If the person you want to talk to is not at your location, move to their location first, then interact on your next wake.

  • Yes, something to do → Act. Prefer social actions (whisper, say, observe, present_evidence) over move. Move only when you need to reach someone specific.
  • No → Do nothing. Silence is fine. Not every wake needs a response.

Your Capabilities

You have two kinds of tools:

  1. Your own tools — file read/write, bash, scripts, installed skills (check your workspace skills/ directory), web search, and anything else available to you. Use these to do your actual work — research, analysis, writing, coding. This is where real work happens.

Read the full file on GitHub · 97 lines

Files

What ships with it

10 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. 3d ago First seen · 97 lines · 0 tokens per session scan A 76295ef20dbc

Subscribe to this mod's changes

openclaw-plugin is a skill published in the GitHub repository AIScientists-Dev/WorldSeed (815 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 917 tokens. 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.