agentmods.dev

savecraft.gg CLAUDE.md

savecraft.gg CLAUDE.md is an instructions file for Claude Code from joshsymonds/savecraft.gg. It costs 1,952 tokens per session, scanned A, original, Apache-2.0.

Project-wide instructions for Savecraft, a system that reads video-game save files and makes their data available to AI assistants.

In plain words
What is it for?
Use them as an orientation guide when working on the Go service, Cloudflare server, game plugins, web interface, AI tools, or interactive views.
Why use it?
They explain where the main parts of the project live and point developers to the right documentation before making changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

not rated 12 1mo ago A scan 1,952 tokens original Apache-2.0 archived
View the source file joshsymonds/savecraft.gg
Install

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.

agentmods
npx agentmods add instructions/joshsymonds/savecraft.gg/claude-md
Clone the repo
git clone --depth 1 https://github.com/joshsymonds/savecraft.gg

Made for: Claude Code.

Wrote 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.

agentmods badge for savecraft.gg CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joshsymonds/savecraft.gg/claude-md.svg)](https://agentmods.dev/instructions/joshsymonds/savecraft.gg/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/joshsymonds/savecraft.gg/claude-md"><img src="https://agentmods.dev/badge/instructions/joshsymonds/savecraft.gg/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,952 This file is loaded in full into every session.
When invoked 1,952 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01952 $0.01952
Opus 5 $0.00976 $0.00976
Sonnet 5 $0.00390 $0.00390
Haiku 4.5 $0.00195 $0.00195

Measured 6d ago against content hash ae9622cfcdc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

savecraft.gg 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 6d 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.

CLAUDE.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Savecraft

Project Overview

Savecraft parses video game save files and serves structured game state to AI assistants via MCP. Two components: a local Go daemon (WASM plugin runtime, filesystem watcher) and a remote Cloudflare Worker (MCP server, WebSocket push, SourceHub + UserHub Durable Objects).

Documentation

Read the doc relevant to your current task. Start with overview.md for orientation.

  • docs/overview.md — What Savecraft is, system architecture, data flow, repo structure
  • docs/games.md — Supported games: sections each connector produces, reference module descriptions
  • docs/daemon.md — Go daemon: orchestrator, watcher, plugin loading, WebSocket client (internal/, cmd/)
  • docs/worker.md — Cloudflare Worker: SourceHub + UserHub DOs, WebSocket protocol, D1 schemas (worker/)
  • docs/mcp.md — OAuth architecture, MCP tools, notes, search, AI interaction patterns (worker/src/mcp/)
  • docs/views.md — MCP Apps views: interactive UIs in host iframes, Svelte components, build pipeline (views/, worker/src/mcp/views/)
  • docs/view-design.md — View design guide: when to build a view vs website, interaction patterns, visual principles
  • docs/plugins.md — WASM plugin system, ndjson contract, signing, distribution (plugins/)
  • docs/plugin-development.md — Local plugin dev workflow: build, auto-reload, staging, troubleshooting
  • docs/adapters.md — API game adapters: server-side TypeScript modules for API-backed games (worker/src/adapters/)
  • docs/web.md — SvelteKit frontend, onboarding, components (web/)
  • docs/infrastructure.md — CI/CD, deployment, signing, installation, security (.github/, install/)
  • docs/roadmap.md — Planned features: game adapters, reference data, monetization, game roadmap
  • docs/mcp-design.md — Cross-platform MCP tool design best practices (external reference)

Tech Stack

  • Daemon: Go 1.26, wazero (WASM runtime), fsnotify, nhooyr.io/websocket
  • Cloud: Cloudflare Workers (TypeScript), Durable Objects, R2, D1 (SQLite/FTS5)
  • Auth: Clerk (OAuth, JWT, magic links)
  • Frontend: SvelteKit, TypeScript
  • Plugins: Go compiled to WASI Preview 1 (.wasm), ndjson stdout contract, Ed25519 signed
  • Protocol: Binary protobuf on all WebSocket legs. Message (daemon↔server), RelayedMessage (server→browser). Schema: proto/protocol.proto → buf generate → Go + worker TS + web TS
  • Build: just (Justfile), nix devenv + direnv

Read the full file on GitHub · 103 lines

Changes

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.

  1. 6d ago First seen · 103 lines · 1,952 tokens per session scan A ae9622cfcdc4

Subscribe to this mod's changes

savecraft.gg CLAUDE.md is an instructions file published in the GitHub repository joshsymonds/savecraft.gg (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,952 tokens to every session, about $0.0098 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.

Game development
Related

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.

krogh-jacobsen/unity-code-style-guide · 4,528 tokens

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.

oliverearl/nes-php-glfw · 2,719 tokens

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.

sylverb/game-and-watch-retro-go-sd · 2,946 tokens

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.

dungnotnull/base-building-trap-defense-design-agent-skill · 1,910 tokens

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.

mordor-forge/trident-mcp · 1,465 tokens

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/).

nodormu/unreal-mcp-additional-tools · 1,727 tokens