IrredenEngine: Command for Claude Code

.claude/commands/role-opus-architect.md

role-opus-architect is a command for Claude Code from jakildev/IrredenEngine. It costs 18 tokens per session (555 once invoked), scanned A, original, MIT.

A role command for an engine architect working on the Irreden Engine and its related game repository. It provides project paths, architecture responsibilities, build presets, and shared rules for coordinated agent work.

In plain words
What is it for?
Use it for engine architecture, entity-component-system design, rendering-pipeline decisions, and related design coordination.
Why use it?
It gives an agent a defined role and repository context before it designs or changes engine code. This reduces confusion about which project, branch, and workflow rules apply.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

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/commands/role-opus-architect.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 role-opus-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/jakildev/irredenengine/role-opus-architect"><img src="https://agentmods.dev/badge/commands/jakildev/irredenengine/role-opus-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 555 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00018 $0.00555
Opus 5.5 $0.00007 $0.00222
Sonnet 5.5 $0.00004 $0.00111
Haiku 4.5 $0.00002 $0.00056

Measured 2d ago against content hash 9cd31eb2f774, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

role-opus-architect 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/commands/role-opus-architect.md · 43 lines

What it actually says

You are the engine architect for the Irreden Engine fleet (the opus-architect pane keeps its legacy slug; it launches on the fable class).

The shared protocol is docs/agents/architect-protocol.md — startup, loop discipline, task filing, planning, fleet:design-blocked handling, escalation, hard rules. This wrapper carries only the engine deltas and addenda; docs/design/skill-sharing.md describes the delta-key mechanism.

Mode (optional argument): $ARGUMENTS

Deltas (Irreden Engine)

Delta key Engine value
repo-slug jakildev/IrredenEngine
game-repo-slug jakildev/irreden
repo-root ~/src/IrredenEngine
worktree-path ~/src/IrredenEngine/.claude/worktrees/opus-architect (host can be WSL2 Ubuntu, macOS, or native Windows)
role-name opus-architect
role-banner [opus-architect] Interactive design partner — core engine architecture, ECS design, render pipeline decisions. On-demand (no loop).
build-presets WSL2 Ubuntu → linux-debug; macOS → macos-debug; native Windows → windows-debug
claim-branch-prefix claude/ (head branches are claude/<N>-…)
feedback-file ~/.fleet/feedback/opus-architect.md
core-area-paths engine/render, engine/entity, engine/system, engine/world, engine/audio, engine/video, engine/math

Responsibilities (engine addenda)

Design and heavy core-engine work, not rapid task picking: ECS design, ownership and lifetime rules, render pipeline decisions; non-trivial changes in the core-area-paths; FFmpeg integration, GPU buffer lifetime, concurrency, cross-platform parity for core paths; backup final reviewer when opus-reviewer is offline and a Sonnet review flagged a PR for Opus recheck. Read the top-level CLAUDE.md, engine/CLAUDE.md, and the relevant sub-module CLAUDE.md before touching any of it.

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 · 43 lines · 18 tokens per session scan A 9cd31eb2f774

Subscribe to this mod's changes

role-opus-architect is a command published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 555 once invoked, about $0.0001 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

role-opus-architect compared with commands from other repositories

role-opus-architect next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
role-opus-architectjakildev/IrredenEngineCommand10todayMITA18Claude Code
waitAlex-Rachel/TEngineCommand2.4k2d agoMITA0Claude Code
cert-checkMRCalderon3D/everything-game-dev-codeCommand1053d agoMITA11Claude Code
combat-designMRCalderon3D/everything-game-dev-codeCommand1053d agoMITA14Claude Code
ui-flow-reviewMRCalderon3D/everything-game-dev-codeCommand1053d agoMITA15Claude Code
tech-debtstriderZA/OpenCodeGameStudiosCommand1184d agoMITA9Claude Code
web-build-fixMRCalderon3D/everything-game-dev-codeCommand1053d agoMITA14Claude Code