Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/bjornmelin/dev-skills/typegpunpx skills add BjornMelin/dev-skills --skill typegpugit clone --depth 1 https://github.com/BjornMelin/dev-skillsWhat 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 | $0.00084 | $0.01158 |
| Opus 5 | $0.00042 | $0.00579 |
| Sonnet 5 | $0.00017 | $0.00232 |
| Haiku 4.5 | $0.00008 | $0.00116 |
Grade A, and why
typegpu 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
24 files 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.
- agents/openai.yaml 297 B
- assets/examples/typegpu-starter.ts 909 B runs code
- assets/templates/typegpu-audit-report.md 623 B
- assets/templates/typegpu-review-checklist.md 1.4 KB
- evals/evals.json 3.8 KB
- evals/trigger-queries.json 3.9 KB
- references/advanced.md 5.3 KB
- references/browser-capability-and-adapter-selection.md 2.4 KB
- references/compute-vs-render-pipeline-design.md 2.3 KB
- references/index.md 666 B
- references/matrices.md 6.3 KB
- references/noise.md 5.1 KB
- references/pipelines.md 10 KB
- references/provenance.json 2.0 KB
- references/sdf.md 5.3 KB
- references/setup.md 4.7 KB
- references/shader-resource-boundaries.md 2.1 KB
- references/shaders.md 17 KB
- references/source-ledger.md 1.6 KB
- references/textures.md 5.2 KB
- references/typegpu-codex-playbook.md 1.5 KB
- references/types.md 5.4 KB
- references/webgpu-runtime-validation.md 1.6 KB
- scripts/audit.mjs 19 KB runs code
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.
- 2d ago First seen · 92 lines · 84 tokens per session scan A 4a23057e9524
typegpu is a skill published in the GitHub repository BjornMelin/dev-skills (6 stars, last pushed 10d ago), with no licence file. It adds 84 tokens to every session and 1,158 once invoked, about $0.0004 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.
Other skills, from other repositories
figma-plugin
Use when building Figma plugins, creating design automation tools, implementing sandbox/UI communication, or working with the Figma Plugin API for node manipulation, styles, and components.
remember
Save important knowledge explicitly to the agent memory.
memory-tip
Tips on using the agent memory tools.
stop-slop
Remove AI-sounding slop from generated text.
tone-of-voice
Apply the company tone of voice to every answer.
backup
Backup utilities exposed through scripts.