IrredenEngine: Skill for Claude Code

.claude/skills/backend-parity/SKILL.md

backend-parity is a skill for Claude Code from jakildev/IrredenEngine. It costs 113 tokens per session (2,531 once invoked), scanned A, original, MIT.

A procedure for keeping OpenGL and Metal rendering backends feature-compatible across Linux, Windows, and macOS. It audits the shader and C++ implementations, ports missing work between GLSL and MSL, and builds and smoke-tests the lagging side.

In plain words
What is it for?
Use it for a full parity audit, a pull-request or commit-range comparison, or to port one named rendering feature between OpenGL and Metal.
Why use it?
It prevents a rendering feature from working on one supported graphics backend but not the other. The build and smoke test help catch ports that only look complete in source code.

Skill for Claude Code

Written for Claude Code: installed under .claude/. 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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/shader_parity_audit.py.

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/skills/backend-parity/SKILL.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 backend-parity

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakildev/irredenengine/backend-parity"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/backend-parity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,531 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 $0.00113 $0.02531
Opus 5.5 $0.00045 $0.01012
Sonnet 5.5 $0.00023 $0.00506
Haiku 4.5 $0.00011 $0.00253

Measured 2d ago against content hash 7254d08472e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backend-parity 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/skills/backend-parity/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

backend-parity

Fleet rules for parity work — host must match the lagging side, build-only is not done, one feature per PR, Opus for math / dispatch / buffer-lifetime ports — live in docs/agents/FLEET.md §"Cross-platform parity (OpenGL ↔ Metal)" and §"Model split". This skill is the port procedure.

Preconditions

  1. Host matches the lagging backend (uname -s): Darwin ports GLSL → MSL on macos-debug; Linux or MinGW/MSYS ports MSL → GLSL on linux-debug / windows-debug. Cross-compilation is not a substitute for the build + smoke.
  2. The lagging preset is already configured; never run cmake --preset (CLAUDE-BASELINE.md §"Hard rules for autonomous fleet roles").
  3. gh auth status succeeds; the skill ends in a PR.
  4. On a feature branch with a clean tree — a parity PR is pure parity work.

Flow

1. Resolve the scope

Take the mode from the trigger phrase or ask:

  • Full audit — walk the whole render tree.
  • PR-scoped — mirror PR <N>; only the files it touched.
  • Commit-range — mirror everything since <ref>.
  • Single feature — port one named file; skip the audit.

The mode goes at the top of the PR body.

2. Enumerate the deviation set

Layout: engine/render/src/opengl/opengl_*.cpp ↔ engine/render/src/metal/metal_*.cpp (headers mirror under engine/render/include/irreden/render/{opengl,metal}/); shaders engine/render/src/shaders/*.glsl (c_/v_/f_/g_ stage prefixes per CLAUDE-BASELINE §Naming) ↔ engine/render/src/shaders/metal/*.metal. One .metal file bundles the vertex + fragment pair — a GLSL v/f pair ports to one .metal file (framebuffer_to_screen.metal is the pattern), and a .metal file ports to both v_<key>.glsl and f_<key>.glsl.

Missing-counterpart audit, both directions, from the repo root:

python3 scripts/shader_parity_audit.py

It prints every unpaired shader with the file it expects and exits 1 on any; the shader-parity workflow runs the same command on every shader PR. The tree keeps the c_ and ir_ prefixes on the Metal side and drops the v_/f_/g_ ones, so do not strip prefixes by hand. A deliberate asymmetry goes in engine/render/src/shaders/parity_allowlist.json: by-design with a reason when the counterpart is bundled or co-located, deferred with a follow_up issue when the port is still owed.

Read the full file on GitHub · 197 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 · 197 lines · 113 tokens per session scan A 7254d08472e8

Subscribe to this mod's changes

backend-parity is a skill published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 2,531 once invoked, about $0.0005 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

backend-parity compared with skills from other repositories

backend-parity next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
backend-parityjakildev/IrredenEngineSkill10todayMITA113Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k2d agoMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100k2d agoApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394kyesterdayMITA36Claude Code
systematic-debuggingobra/superpowersSkill315k5d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code