Borrowing it
Nothing to install: this file belongs to Gnidreve/Genesis-World-MCP. 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/Gnidreve/Genesis-World-MCP/main/AGENTS.mdgit clone --depth 1 https://github.com/Gnidreve/Genesis-World-MCPWrote 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/gnidreve/genesis-world-mcp/agents-md)<a href="https://agentmods.dev/instructions/gnidreve/genesis-world-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gnidreve/genesis-world-mcp/agents-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 | $0.09106 | $0.09106 |
| Opus 5 | $0.04553 | $0.04553 |
| Sonnet 5 | $0.01821 | $0.01821 |
| Haiku 4.5 | $0.00911 | $0.00911 |
Grade A, and why
Genesis-World-MCP AGENTS.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 4d 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 — 581 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — CAS genesisWorld MCP
Guidance for any AI agent or developer working in this repository.
What this is
An MCP server for the CAS genesisWorld
REST Webservice v7.0 — aiming to be the genesisWorld MCP, not a thin
wrapper. The full upstream API surface is committed at the repo root as
swagger.json and is the single source of truth /
cross-reference for every tool.
The project plan lives in ROADMAP.md (machine-readable,
stable item IDs). Current state: P0–P8, P10–P14 done (P6.4 OAuth2
blocked — no OAuth2-capable installation for ~6 months; P9 document
upload is the next planned phase). 69 tools: 43 read / 26 write, 7 of
them flows;
flow results are compacted by default (P7); result cap + request logging
in place; npm (cas-genesis-world-mcp) and Docker Hub
(vaatu/cas-genesis-world-mcp) publish pipelines are live, fully
automatic on a package.json version bump (NPM_TOKEN /
DOCKERHUB_TOKEN repo secrets already set). New work = new ROADMAP
items first.
Release checklist: see "Publishing" below — the short version is
bump version in package.json → commit → push to main. The server's
own registered name and version (src/index.ts) are both read from
package.json at runtime rather than duplicated, so there's nothing else
to keep in sync.
Standing orders — READ FIRST
- Docs stay in sync, always. Any commit that adds/changes/removes a
tool, flow, resource, flag, or config variable must update
README.md, the tool tables in this file, and the matchingROADMAP.mditem status in the same commit. The maintainer will not remind you; this rule is the reminder. - ROADMAP.md is the progress ledger. Work items are picked from it, and their status is flipped when done. New scope is appended as new items first, then implemented.
- Structural proposals are manifested here before implementation. If you want to change architecture/conventions, write the proposal into this file (or ROADMAP.md) in its own commit so the maintainer can see it — do not just restructure code silently.
- Never document unimplemented features as existing. README.md
describes what
mainactually does; the future lives in ROADMAP.md.
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.
- 4d ago Changed · +72 lines · +1,238 tokens per session 6d8512a40d6e
- 8d ago First seen · 509 lines · 7,868 tokens per session scan A ded7545d4804
Genesis-World-MCP AGENTS.md is an instructions file published in the GitHub repository Gnidreve/Genesis-World-MCP (1 stars, last pushed 6d ago), licensed MIT. It adds 9,106 tokens to every session, about $0.0455 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 instructions, from other repositories
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.
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).
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).
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.
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.