sounio-render

sounio-render is a skill for Claude Code, Codex from Sounio-lang/sounio. It costs 49 tokens per session (1,010 once invoked), scanned A, original, Apache-2.0.

Development guidance for Sounio's rendering platform, covering its shared rendering library, examples, website previews, and graphics-card backends.

In plain words
What is it for?
Use it to edit rendering modules or examples, add drawing primitives, run validation checks, and update website showcase previews.
Why use it?
It records the project rules and checks needed to change rendering code without breaking the rendering pipeline or its examples.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/sprint53_render_platform_gate.sh.

Good fit Use it to edit rendering modules or examples, add drawing primitives, run validation checks, and update website showcase previews.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Sounio-lang/sounio
agentmods
npx agentmods add skills/sounio-lang/sounio/sounio-render

Made for: Claude Code, Codex.

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 sounio-render

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sounio-lang/sounio/sounio-render"><img src="https://agentmods.dev/badge/skills/sounio-lang/sounio/sounio-render.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,010 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 $0.00049 $0.01010
Opus 5 $0.00024 $0.00505
Sonnet 5 $0.00010 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 10d ago against content hash a153f1637f19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sounio-render 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 10d 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.

skills/sounio-render/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sounio Render Platform

Overview

Covers the CPU-rasterizer render pipeline, flagship epistemic scenes, GPU preview emitters, and website showcase assets.

Six modules in stdlib/render/ define the shared API: types.sio, framebuffer.sio, rasterizer.sio, scene.sio, pipeline.sio, epistemic.sio. All render examples are self-contained (no use imports) and output PPM P3 format to stdout.

Workflow

1) Check stdlib/render/ first

  • All six modules must pass souc check before any example edits.
  • Adding a new primitive (e.g. rasterize_rect)? Add it to rasterizer.sio, verify with a souc run smoke test.
  • Helper functions must precede callers — no forward references in Sounio.

2) Complete or edit a render example

  • Examples are self-contained: inline all needed functions (no use imports).
  • Use [i64; 65536] framebuffer arrays; [i64; 16384] is undersized for the shared API.
  • Effect annotations required: with IO, Mut, Div, Panic on any function calling raster helpers.
  • Negative float literals: write 0.0 - 0.471, not -0.471 (Sounio constraint).
  • var for mutable locals, let for immutable. No pub, no Rust macros.
  • Keep var fb_r: [i64; 65536] as flat locals in main() — never instantiate Framebuffer struct on the stack (it is ~2 MB).

3) Run the PPM gate

SOUC=./bin/souc
bash scripts/sprint53_render_platform_gate.sh
# Spot-check a render:
$SOUC run examples/render/uncertainty_field.sio > /tmp/uf.ppm && head -3 /tmp/uf.ppm
# Expected: P3 / 128 128 / 255

PPM dimensions verified per example:

Example Width Height
triangle_basic.sio 128 128
triangle_ppm.sio 128 128
cube_wireframe.sio 192 192
uncertainty_ppm.sio 128 128
uncertainty_field.sio 128 128
causal_dag.sio 256 128
quaternion_rotation.sio 192 192

4) GPU emitter changes

  • Each GPU render file (ptx_render.sio, metal_render.sio, spirv_render.sio, wgsl_render.sio in self-hosted/gpu/) is additive-only.
  • Existing main() must continue working; new scene-aware functions are added alongside it.
  • Scene contract: add struct RenderScene + fn render_scene_default() (Sprint 54 pattern).
  • Gate: bash scripts/sprint54_gpu_contract_gate.sh

Read the full file on GitHub · 80 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 80 lines · 49 tokens per session scan A a153f1637f19

Subscribe to this mod's changes

sounio-render is a skill published in the GitHub repository Sounio-lang/sounio (6 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,010 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

vera-language

Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.

aallan/vera · 61 tokens

vera-language

Write programs in the Vera programming language. Use when asked to write, edit, debug, or review Vera code (.vera files). Vera is a statically typed, purely functional language with algebraic effects, mandatory contracts, and typed slot references (@T.n) instead of variable names.

aallan/vera · 61 tokens

lifeblood-mcp

Use when an agent should work with Lifeblood's MCP semantic-code tools: analyzing C# or Unity workspaces, querying symbols/dependencies/blast radius/file impact/test impact, checking architectural invariants, validating edits with compilecheck/diagnose, or choosing the right Lifeblood tool instead of grep-style…

user-hash/Lifeblood · 70 tokens

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens