IrredenEngine: Instructions file for Claude Code

CLAUDE.md

IrredenEngine CLAUDE.md is an instructions file for Claude Code from jakildev/IrredenEngine. It costs 1,476 tokens per session, scanned A, original, MIT.

A set of project instructions for Irreden Engine, an isometric voxel game engine using C++ and Lua. It explains the engine layout, build workflow, and which directory-specific rules to read.

In plain words
What is it for?
Use it when modifying the engine, its systems, pipelines, demos, editors, or Lua-driven creations. It helps locate architecture documentation and the applicable instructions for a directory.
Why use it?
It gives coding agents the project conventions and build guidance needed to work in the correct part of the engine. It also prevents private game or editor projects from being treated as if they shared the engine’s rules.

Instructions file for Claude Code

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

This is jakildev/IrredenEngine's own configuration. It tells Claude Code how to work on IrredenEngine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything IrredenEngine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jakildev/IrredenEngine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jakildev/IrredenEngine/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jakildev/IrredenEngine

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 IrredenEngine CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jakildev/irredenengine/claude-md/github.svg)](https://agentmods.dev/instructions/jakildev/irredenengine/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jakildev/irredenengine/claude-md"><img src="https://agentmods.dev/badge/instructions/jakildev/irredenengine/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.

agentmods 80×15 button for IrredenEngine CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jakildev/irredenengine/claude-md"><img src="https://agentmods.dev/badge/instructions/jakildev/irredenengine/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,476 This file is loaded in full into every session.
When invoked 1,476 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01476 $0.01476
Opus 5.5 $0.00590 $0.00590
Sonnet 5.5 $0.00295 $0.00295
Haiku 4.5 $0.00148 $0.00148

Measured 2d ago against content hash e186831c6edd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

IrredenEngine 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 2d 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Irreden Engine

Isometric voxel game engine built on an archetype-based ECS. C++ handles the engine, systems, and pipelines. LuaJIT 2.1 (via sol2) drives entity creation and game logic in creations.

docs/agents/AGENTS-ARCHITECTURE.md has the full long-form architecture reference. Module-specific details live in CLAUDE.md files nested under engine/, engine/prefabs/, and creations/ — read the most specific one for whatever directory you're working in.

Private implementations (games, editors, experiments) layered on top of the engine may live in their own gitignored subdirectories under creations/ and may define their own conventions, review criteria, workflows, or even their own repo. The skills in .claude/skills/ are engine-level and generic; when working inside such a subdirectory, always read that subdirectory's own CLAUDE.md first — its rules override the engine baseline for that scope.

Cross-cutting baseline — naming, style, the ECS footgun, the rules for what belongs in a CLAUDE.md, Bash tool restrictions, and cross-repo information isolation live in docs/agents/CLAUDE-BASELINE.md. Read that file alongside this one and treat its sections as if inlined here. Creations inherit the same baseline by reference; see docs/design/claude-md-sharing.md for the mechanism and opt-out form.


Where to find things

You need… Read…
Coding conventions (ECS, naming, IRMath, ownership, comment style) docs/agents/CLAUDE-BASELINE.md
Module-specific patterns (ECS, prefabs, render, math, system, etc.) the nearest CLAUDE.md (loaded automatically when you open a file in that subtree)
Long-form architecture reference (ECS internals, render pipeline, coordinate systems, Lua integration) docs/agents/AGENTS-ARCHITECTURE.md
Build commands and environment setup (Linux/WSL, Windows, macOS) docs/agents/BUILD.md
Validators — what proves a change (tests, harnesses, ratchets, CI) docs/agents/VALIDATION.md
Fleet workflow (parallel agents, PRs, cursor cues, design escalation, model split, labels, clean-exit policy, fix-forward, feedback) docs/agents/FLEET.md
Skills (named workflows like simplify, commit-and-push, review-pr) .claude/skills/ — each has its own SKILL.md
Shared skill flows (fleet skills factored for cross-repo reuse) docs/agents/skills/ — canonical flows; each repo's SKILL.md is a thin wrapper (mechanism: docs/design/skill-sharing.md)
Roles (autonomous personas — worker, reviewer, merger, architect) .claude/commands/role-*.md
Standing objectives (the human-owned "what" above epics) docs/design/objectives/
Task queue (when running fleet roles) fleet-queue-list or gh issue list --label fleet:queued --repo jakildev/IrredenEngine
Cross-repo info isolation rule (engine repo public, game repo private) docs/agents/CLAUDE-BASELINE.md §"Cross-repo information isolation"

Read the full file on GitHub · 92 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. 2d ago First seen · 92 lines · 1,476 tokens per session scan A e186831c6edd

Subscribe to this mod's changes

IrredenEngine CLAUDE.md is an instructions file published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 1,476 tokens to every session, about $0.0059 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 2026-11-07.

Related

IrredenEngine CLAUDE.md compared with instructions from other repositories

IrredenEngine CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
IrredenEngine CLAUDE.mdjakildev/IrredenEngineInstructions file10todayMITA1,476Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA1,907GitHub Copilot