Borrowing it
Nothing to install: this file belongs to oframe/ogpu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/oframe/ogpu/main/.claude/skills/naga-setup/SKILL.mdgit clone --depth 1 https://github.com/oframe/ogpuWrote 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/skills/oframe/ogpu/naga-setup)<a href="https://agentmods.dev/skills/oframe/ogpu/naga-setup"><img src="https://agentmods.dev/badge/skills/oframe/ogpu/naga-setup/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.
<a href="https://agentmods.dev/skills/oframe/ogpu/naga-setup"><img src="https://agentmods.dev/badge/skills/oframe/ogpu/naga-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00000 | $0.01959 |
| Opus 5.5 | $0.00000 | $0.00784 |
| Sonnet 5.5 | $0.00000 | $0.00392 |
| Haiku 4.5 | $0.00000 | $0.00196 |
Grade A, and why
naga-setup 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
naga-setup
Wire a repo so every WGSL edit is compiled by naga immediately, and the whole
shader tree can be checked in one command. WGSL errors otherwise only surface in
the browser console after a reload — this collapses that loop to zero.
The thing to keep straight
A working setup is four artifacts, and they arrive by different routes:
| Artifact | Travels with a git clone? |
|
|---|---|---|
| Repo config | .claude/settings.json hook — runs naga after each Edit/Write of a .wgsl, exits 2 on failure so the compiler error blocks and gets fixed in the same turn |
yes |
scripts/validate-shaders.mjs + npm entry — batch check for CI or a refactor that touched many shaders; the hook only sees files an agent writes, the script sees all of them |
yes | |
| Local toolchain | naga binary |
no |
jq binary |
no |
So a fresh clone of an already-wired repo still has half a setup: a hook that
fires and does nothing, because naga isn't on the machine. That's why step 1 is
the toolchain and not the config. Check each artifact, install whichever are
missing, and when all four are present say so and stop — re-adding the hook just
duplicates it.
Steps
1. Check the local toolchain
naga --version
jq --version
Missing naga makes everything else inert, so fix it first — and offer to run the
install rather than just quoting it, since on a fresh clone this is usually the
only gap:
brew install naga-cli # macOS / Linux — NOT `brew install naga`, that formula
# is a Snake game and collides on the same binary name
cargo install naga-cli # any platform with Rust
If naga --version succeeds but prints something that isn't a wgpu version
string, that's the Snake game — people hit this often enough to be worth checking
rather than assuming a zero exit means the compiler.
jq reads the tool payload for the hook. Usually present on macOS; brew install jq
otherwise.
2. Install the hook
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.
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.
- 12d ago Changed · +4 lines c6fa5d355c22
- 1mo ago First seen · 165 lines · 0 tokens per session scan A e71f0c468c75
naga-setup is a skill published in the GitHub repository oframe/ogpu (163 stars, last pushed 3d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 1,959 tokens. 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 2026-08-30.
Other skills, from other repositories
regression-suite
Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.
soak-test
Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
team-polish
Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.
smoke-check
Critical-path smoke gate before QA hand-off — runs the automated suite. A failed check means the build is not QA-ready.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.