Borrowing it
Nothing to install: this file belongs to albumentations-team/albucore. 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/albumentations-team/albucore/main/.codex/skills/albucore-benchmarks/SKILL.mdgit clone --depth 1 https://github.com/albumentations-team/albucoreWrote 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/albumentations-team/albucore/albucore-benchmarks)<a href="https://agentmods.dev/skills/albumentations-team/albucore/albucore-benchmarks"><img src="https://agentmods.dev/badge/skills/albumentations-team/albucore/albucore-benchmarks/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/albumentations-team/albucore/albucore-benchmarks"><img src="https://agentmods.dev/badge/skills/albumentations-team/albucore/albucore-benchmarks.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 | $0.00048 | $0.01302 |
| Opus 5 | $0.00024 | $0.00651 |
| Sonnet 5 | $0.00010 | $0.00260 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
albucore-benchmarks 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Albucore Benchmarks
Before designing a performance comparison, read ../performance-optimization/SKILL.md and
../../../docs/performance-optimization.md completely. Extend the benchmark along the dimension that controls the
candidate, such as label density for bincount, table and channel layout for LUTs, or output size and dtype for random
generation.
Use exactly one CPU thread per process for every candidate, following the thread controls in the canonical performance guide. Benchmark additional thread counts only when the user explicitly requests thread scaling.
Layout
benchmarks/- Python timing scripts. Run from repo root:uv run python benchmarks/<script>.py.benchmarks/timing.py- Sharedmedian_mshelper for scripts executed aspython benchmarks/foo.py../benchmark.sh- Dataset-driven runner; expects an externalbenchmarkpackage that is not always present in-tree. Prefer synthetic scripts for CI-style checks.benchmarks/benchmark_router_synthetic.py- Times public routers on syntheticuint8andfloat32arrays: HWC, plus NHWC formean,std, andmean_stdonly.benchmarks/compare_router_json.py- Builds a Markdown table from two JSON outputs.benchmarks/benchmark_resize3d_tensor.py- Times direct Tensor, zero-copy Tensor→NumPy→Tensor, and publicresize3droutes for contiguous and channel-last-strided CPUCDHWTensors.benchmarks/benchmark_warp_affine3d.py- Times full single-volume NumPyDHWCaffine paths, including the NumPy→Torch bridge and public router.benchmarks/benchmark_warp_affine3d_tensor.py- Times native Torch affine-grid, manual-grid and coverage-fill probes, and public single-volumeCDHWrouting.
Canonical Shape Grid
Benchmark shape sweeps use channel-last Albucore conventions.
HWC images:
128x160with 1, 3, 9 channels - small / warm-cache, non-square.240x320with 1, 3, 9 channels - mid-size crop, non-square.480x640with 1, 3, 9 channels - typical augmentation training crop, non-square.768x1024with 1, 3, 9 channels - high-res / full-image pass, non-square.
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 Changed · +3 lines d4013c6acc7f
- 10d ago First seen · 84 lines · 48 tokens per session scan A 6207800e02b0
albucore-benchmarks is a skill published in the GitHub repository albumentations-team/albucore (123 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,302 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 2026-08-30.
Other skills, from other repositories
langchain_patterns
Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
langchain_patterns
Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
api-debugging
Systematic approach to debugging REST APIs, HTTP errors, authentication issues, and network problems. Use when the user has API errors, status code issues, timeout problems, or needs help troubleshooting HTTP requests.
writing-assistant
Helps improve writing quality — emails, documents, blog posts, and technical content. Provides editing, tone adjustment, structure suggestions, and grammar fixes. Use when the user asks to write, edit, review, or improve any text content.
document-assistant
OwnPilot official general skill for drafting, editing, restructuring, and reviewing long-form documents, reports, proposals, policies, and documentation. Use when the user asks to create or improve a document.
meeting-notes
OwnPilot official general skill for converting rough meeting notes, transcripts, and call summaries into decisions, action items, owners, risks, and follow-ups. Use when the user provides meeting content or asks for notes.