Borrowing it
Nothing to install: this file belongs to AndreiNicu/World-Forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AndreiNicu/World-Forge/main/CLAUDE.mdgit clone --depth 1 https://github.com/AndreiNicu/World-ForgeWrote 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.
[](https://agentmods.dev/instructions/andreinicu/world-forge/claude-md)<a href="https://agentmods.dev/instructions/andreinicu/world-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/andreinicu/world-forge/claude-md/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.
<a href="https://agentmods.dev/instructions/andreinicu/world-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/andreinicu/world-forge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.25085 | $0.25085 |
| Opus 5.5 | $0.10034 | $0.10034 |
| Sonnet 5.5 | $0.05017 | $0.05017 |
| Haiku 4.5 | $0.02508 | $0.02508 |
Grade A, and why
World-Forge CLAUDE.md 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 2d ago.
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 — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Standing context for AI coding agents (Claude Code, Antigravity, similar) working on this repository. This file is read first on every session start. It tells you what this project is, what the load-bearing architectural decisions are, and what rules govern safe modification of the pipeline files.
What this repository is
World Forge is a multi-agent pipeline for building immersive roleplay worlds for SillyTavern. It is not application code in the traditional sense — it is a curated collection of agent specifications (markdown), templates (markdown and JSON), and orchestration logic (markdown) that together define a structured creative writing pipeline.
The pipeline is designed to run inside an agentic VS Code extension (typically Kilo Code; the formerly-recommended Roo Code was retired May 15, 2026). When invoked, it walks a user from a raw idea through 5+ phases of structured drafting and validation, producing a complete SillyTavern-ready world package.
The repository is the pipeline itself. Editing files here changes how the pipeline behaves on its next run. There is no compilation step, no test suite, no deployment — files are read directly by the runtime agent.
What this repository is NOT
- Not a SillyTavern fork or extension. SillyTavern is the runtime environment that consumes the pipeline's outputs. This repo produces files for SillyTavern; it does not modify SillyTavern itself.
- Not a runtime engine. The pipeline does not execute — it is consumed by an agentic IDE extension (Kilo Code) that orchestrates LLM calls. Do not add execution logic, build steps, or deployment configuration.
- Not a code project. The "code" here is markdown agent specifications. Treat them as you would treat carefully-versioned prose documents, not as source code.
- Not for editing during pipeline runs. When a user is actively running
/worldforge start, the pipeline files are being read by the runtime agent. Editing them mid-run produces undefined behavior.
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.
- 2d ago Changed · +5 lines · +468 tokens per session 59983c061c2d
- 2mo ago First seen · 423 lines · 24,617 tokens per session scan A 88c5339f4c68
World-Forge CLAUDE.md is an instructions file published in the GitHub repository AndreiNicu/World-Forge (84 stars, last pushed 2d ago), licensed MIT. It adds 25,085 tokens to every session, about $0.1003 per session on Opus 5.5. 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.
World-Forge CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| World-Forge CLAUDE.mdAndreiNicu/World-Forge | Instructions file | 84 | 2d ago | MIT | A | 25,085 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |