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.svg" alt="Measured on agentmods" 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 | $0.24617 | $0.24617 |
| Opus 5 | $0.12308 | $0.12308 |
| Sonnet 5 | $0.04923 | $0.04923 |
| Haiku 4.5 | $0.02462 | $0.02462 |
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 8d 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 — 423 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.
- 8d 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 (74 stars, last pushed 1mo ago), licensed MIT. It adds 24,617 tokens to every session, about $0.1231 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.