Borrowing it
Nothing to install: this file belongs to Txpple/fvtt-mcp-artificer. 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/Txpple/fvtt-mcp-artificer/main/CLAUDE.mdgit clone --depth 1 https://github.com/Txpple/fvtt-mcp-artificerWrote 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/txpple/fvtt-mcp-artificer/claude-md)<a href="https://agentmods.dev/instructions/txpple/fvtt-mcp-artificer/claude-md"><img src="https://agentmods.dev/badge/instructions/txpple/fvtt-mcp-artificer/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/txpple/fvtt-mcp-artificer/claude-md"><img src="https://agentmods.dev/badge/instructions/txpple/fvtt-mcp-artificer/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 | $0.01870 | $0.01870 |
| Opus 5.5 | $0.00748 | $0.00748 |
| Sonnet 5.5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
fvtt-mcp-artificer 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 1mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
fvtt-mcp-artificer
Image-generation MCP server for D&D table art, backed by the Gemini image API (the Nano
Banana models). It exposes a small set of Foundry-specific tools so Claude can author prompts,
generate art, edit existing art, cut tokens to alpha, curate the results by actually looking at
them, and hand the winners to the Foundry pipeline (upload-asset → set-actor-art /
add-journal-image in fvtt-mcp-dnd5e).
Status: v1.0.0 shipped 2026-09-19 on the Gemini API. The first version of this server wrapped a local ComfyUI install with FLUX models and a trained house-style LoRA. That direction is dead: the local pipeline took many iterations per usable image, the LoRA never delivered a consistent look, and the owner was already feeding its output to Nano Banana to fix. ComfyUI, the models, the training toolkit, and the corpus are deleted from the machine. Nothing local remains. See ROADMAP.md for the rebuild milestones; the ComfyUI-era notes are in notes/archive/ for history only and describe nothing that still exists.
Scope (binding)
- Foundry-specific by decree, NOT a generic Gemini image bridge. Tools speak Foundry vocabulary and get tweaked freely for Foundry work. Do not generalize.
- API only. No local models, no local inference, no GPU dependency. Do not reintroduce a local backend or a backend abstraction. One client, one provider.
- Separate from
fvtt-mcp-dnd5e. That server is scoped to Foundry content authoring and must not couple to image generation. This server never talks to the Foundry bridge; the handoff between them is files on disk + the dnd5e MCP's upload tools. - Same house philosophy as the rest of the family: tools do, skills decide. Correctness
(model selection per kind, ratio and size, post-processing, cutout, file conventions, the Pro
cost gate) lives in tested tools here; judgment (prompt craft, curation taste, which reference
images to attach, which actor/journal gets the art) lives in the
illustration-builderskill. - Everything is in git. The tool is this repo; the approved art is in the campaign repos.
The only machine-side state is the API key in
.env.
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.
- 1mo ago Changed · +11 tokens per session 6a66264c328e
- 1mo ago Changed · +24 lines · +649 tokens per session a51e19f664aa
- 2mo ago First seen · 93 lines · 1,210 tokens per session scan A 5551be26a23d
fvtt-mcp-artificer CLAUDE.md is an instructions file published in the GitHub repository Txpple/fvtt-mcp-artificer (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,870 tokens to every session, about $0.0075 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 2026-08-31.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.