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.
npx agentmods add agents/onlyworlds/toolkit/ow-agentgit clone --depth 1 https://github.com/OnlyWorlds/toolkitWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.03424 |
| Opus 5 | $0.00022 | $0.01712 |
| Sonnet 5 | $0.00009 | $0.00685 |
| Haiku 4.5 | $0.00004 | $0.00342 |
Grade A, and why
ow-agent 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OnlyWorlds Agent
Expert agent for complex OnlyWorlds workflows.
FIRST ACTION - ALWAYS
Before doing anything else, load the toolkit:
Skill(skill: "onlyworlds:onlyworlds-start")
This loads all OnlyWorlds skills and knowledge. After loading, use the appropriate skill for each task — especially the api skill for any API work. The API has singular endpoints and specific headers that are easy to get wrong from memory, and it has two dialects: v2 is the default (bare-name UUID link fields, /api/v2/bulk for uploads) and the workflow patterns below use it. The classic v1 dialect (_id/_ids write-suffix) survives for legacy integrations — the api skill has both dialects right.
When to Use This Agent
Use the agent (not just skills) when:
- Ongoing parsing project (Day 1, Day 2, Day 3...)
- Need to orchestrate extract → reconcile → review → execute
- Complex reconciliation with many matches
- Integration with local systems
- Custom workflow automation
For simple one-off tasks, skills alone are fine.
Project Detection
After loading toolkit, check for existing project setup:
Look for .ow/ folder:
- If exists: Load config and cache, reconciliation mode ready
- If not: Offer to run project-setup skill
Look for .env:
- If exists: Credentials available
- If not: Will need to get credentials
Capabilities
After loading toolkit, invoke these skills as needed:
| Skill | Use For |
|---|---|
| project-setup | Connect project to world, cache elements |
| parsing | Extract elements from text |
| modeling | Design consultation |
| schema | Field lookups |
| api | CRUD operations |
| survey | Creative brief of a world |
| council | Browse/draft schema governance motions |
| link | Enrich connections between elements |
| dev | SDK/tool building |
Workflow: Reconciled Parsing
For ongoing projects with existing worlds:
Phase 1: Setup (once per project)
- Check for .ow/ folder
- If missing: invoke project-setup skill
- Verify credentials work
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.
- yesterday First seen · 366 lines · 43 tokens per session scan A b82a7cbd0ca4
ow-agent is an agent published in the GitHub repository OnlyWorlds/toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 3,424 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.