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/wesleysalzer/gamecodex/claude-mdgit clone --depth 1 https://github.com/WesleySalzer/GameCodexWrote 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/wesleysalzer/gamecodex/claude-md)<a href="https://agentmods.dev/instructions/wesleysalzer/gamecodex/claude-md"><img src="https://agentmods.dev/badge/instructions/wesleysalzer/gamecodex/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 | $0.01291 | $0.01291 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
GameCodex 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GameCodex Monorepo
Free and open source MCP server for game developers — 950+ docs across 29 engines, structured workflows, and guidance. MIT licensed.
v1.0.0 shipped 2026-04-17. Active feature development has stopped. Project is in maintenance mode.
Monorepo Structure
GameCodex/
├── packages/
│ ├── server/ <- MCP server (5 tools, 950+ docs, 29 engines)
│ └── site/ <- Marketing site (Next.js)
├── package.json <- npm workspaces root
└── CLAUDE.md <- This file
Commands (run from root)
npm install # install all workspace deps
npm run build # build server (tsc → packages/server/dist/)
npm run build:site # build site (next build)
npm run build:all # build everything
npm run dev # server watch mode
npm run dev:site # site dev server
npm start # start MCP server
npm run typecheck # tsc --noEmit on server
npm test # run all tests
npm run lint:site # eslint on site
Server (packages/server/)
- Entry:
src/server.ts— MCP server setup, 5-tool registration - Tool registry:
src/tool-registry.ts— centralized registration with analytics and error handling - Tool interface:
src/tool-definition.ts— metadata: isReadOnly, isConcurrencySafe, isDestructive (fail-closed defaults) - 5 tools:
src/tools/— project.ts, design.ts, docs.ts, build.ts, meta.ts - Handler utilities:
src/tools/— existing handler functions delegated to by the 5 tools - Core systems:
src/core/— personality, project-store, health-tracker, search, docs, modules, vector search, error-helpers, response-enhancer, help-generator - Knowledge base:
docs/— core (52) + 29 engine modules (957 total docs) - Config dir:
~/.gamecodex/(projects, embeddings, learning progress)
Tool Inventory (v1.0.0 — 5 tools, all free)
| Tool | Actions | What it does |
|---|---|---|
project |
help, hello, get, set, suggest, decide, goal, complete_goal, clear_goals, milestone, note, recall, clear_notes, health, scope, add_feature, list, session | Interactive AI assistant — onboarding, project state, goals, decisions, scope health. Personality adapts to genre/phase. |
design |
help, gdd, phase, scope_check, launch, store_page, pricing, marketing, trailer, patterns | Plan + ship — GDD, phase checklists, scope analysis, marketing guidance, architecture patterns |
docs |
help, search, get, browse, modules | Knowledge base — search/browse 950+ game dev docs across 29 engines |
build |
help, scaffold, code, assets, debug, review | Make things — scaffold projects, generate code, asset pipeline, debug errors, review architecture |
meta |
help, status, analytics, modules, health, about | Server internals — diagnostics, module discovery, help |
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.
- 3d ago First seen · 103 lines · 1,291 tokens per session scan A 125857eeb917
GameCodex CLAUDE.md is an instructions file published in the GitHub repository WesleySalzer/GameCodex (4 stars, last pushed 2mo ago), licensed MIT. It adds 1,291 tokens to every session, about $0.0065 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
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
roblox-brain AGENTS.md
AGENTS.md instructions for TabooHarmony/roblox-brain, covering agents.md: guide for ai agents and contributors, what this repo is, architecture: progressive disclosure, skill file structure and skill title.
godot-mcp-bridge CLAUDE.md
Instructions for TomasLucasUTN/godot-mcp-bridge, covering godot-mcp-bridge — project guide, adding or changing a tool, dev / test loop, tests and gotchas.
mcp-unity CLAUDE.md
Instructions for CoderGamester/mcp-unity, a project described as: Model Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Windsurf and other IDEs.
uefn-verse-mcp CLAUDE.md
Claude Code instructions for quangdang46/uefn-verse-mcp, covering uefn-mcp — ai agent context, architecture, key files, tool surface and rules.
uefn-verse-mcp AGENTS.md
AGENTS.md instructions for quangdang46/uefn-verse-mcp, covering agents.md and for ai agents.