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 instructions/deployfaith/hermes_worldkit_mcp/agents-mdgit clone --depth 1 https://github.com/DeployFaith/Hermes_WorldKit_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/deployfaith/hermes_worldkit_mcp/agents-md)<a href="https://agentmods.dev/instructions/deployfaith/hermes_worldkit_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/deployfaith/hermes_worldkit_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 | $0.00420 | $0.00420 |
| Opus 5 | $0.00210 | $0.00210 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
Hermes_WorldKit_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 5d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository identity
This repository is the separate, first-party WorldKit MCP control plane. It is not WorldKit Core and is not a base dependency of the WorldKit Godot adapter.
Hard boundaries
- Do not add this repository as a dependency of WorldKit Core or
addons/hermes_worldkit. - The Godot component is an optional
EditorPlugin, installable ataddons/worldkit_mcp_bridge. - The Python process is a FastMCP stdio server for agents and a localhost-only WebSocket server for the outbound Godot editor connection.
- Require protocol-v2 mutual nonce/HMAC authentication and exact canonical project-root pinning before accepting a bridge client. Never transmit or log the raw token.
- Bind and connect only to literal loopback addresses. Reject browser Origin headers and require one atomically claimed editor client.
- Expose only explicit allowlisted operations. No terminal, shell, arbitrary file writes, GDScript evaluation, generic method invocation, unrestricted property mutation, runtime autoload, or project-setting mutation.
- Selection operations require the exact inspected scene token and may address only canonical, owned, non-internal nodes under the current edited-scene root.
- Bound editor-main-thread work, request queues, scene traversal, and selection serialization.
- Every request and response carries a request ID. Failures use stable structured error codes.
- Every MCP tool has a clear docstring and strict-client-friendly input schema: no Optional/union parameters and no
anyOf.
Vertical-slice tool allowlist
worldkit_statusworldkit_capabilitiesworldkit_scene_summaryworldkit_selected_nodesworldkit_select_node(node_path, expected_scene_token)
Validation discipline
Use the project-local .venv via uv. Run Python tests, lint, server import, and generated FastMCP schema checks. Godot headless parsing is valuable but is not editor E2E. Never claim editor E2E without actually running an editor and exercising the plugin.
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.
- 5d ago First seen · 31 lines · 420 tokens per session scan A 26ea17cc575a
Hermes_WorldKit_MCP AGENTS.md is an instructions file published in the GitHub repository DeployFaith/Hermes_WorldKit_MCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 420 tokens to every session, about $0.0021 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
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).