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 instructions/albumentations-team/albucore/agents-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/instructions/albumentations-team/albucore/agents-md)<a href="https://agentmods.dev/instructions/albumentations-team/albucore/agents-md"><img src="https://agentmods.dev/badge/instructions/albumentations-team/albucore/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02394 | $0.02394 |
| Opus 5 | $0.01197 | $0.01197 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
albucore AGENTS.md 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 5d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex AI Development Guidelines for Albucore
This document provides guidelines and conventions for AI assistants (particularly Codex) when working on the Albucore codebase.
Project Overview
Albucore is a high-performance image processing library that provides optimized atomic functions for image manipulation. It serves as the foundation for AlbumentationsX and focuses on:
- Maximum performance through multiple backend implementations (NumPy, OpenCV, custom)
- Supported dtypes: uint8 and float32 only (no float64)
- Backend routing is based ONLY on performance — benchmark before choosing. If LUT is slower, don't use it.
- Consistent API across different image types and shapes
Core Documentation
Please familiarize yourself with these key documents:
-
Image Shape Conventions - CRITICAL rules about image shapes
- All images must have an explicit channel dimension
- Grayscale images use shape
(H, W, 1), not(H, W) - Consistent dimension indexing:
shape[-1]is channels,shape[-2]is width,shape[-3]is height
-
Decorators - Decorator usage and patterns
@preserve_channel_dim- Maintains single-channel shape@clipped- Clips to valid dtype range@float32_io/@uint8_io- Type conversion wrappers
-
Performance Optimization - Performance best practices
- LUT operations and float32 dtype management
- Backend selection strategies
- Memory layout considerations
- Benchmarking guidelines
-
Public API - Public routers, star exports, and
albucore.functionscompatibility shims -
PyTorch Optimization - Eager CPU Torch contracts, full-path benchmarks, Tensor/NumPy bridge costs, profiling, allocation, layout, and threading decisions
-
NumKong Performance - NumKong vs OpenCV/NumPy/LUT benchmark tables and methodology
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.
- 5d ago First seen · 278 lines · 2,394 tokens per session scan A 0e38b925b45f
albucore AGENTS.md is an instructions file published in the GitHub repository albumentations-team/albucore (123 stars, last pushed 8d ago), licensed MIT. It adds 2,394 tokens to every session, about $0.0120 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 instructions, from other repositories
ApraPipes CLAUDE.md
Claude Code instructions for Apra-Labs/ApraPipes, covering claude.md - aprapipes declarative pipeline, current phase: sprint 12 - windows integration test fix, sdk structure (complete), critical rules and 1. build and test before commit (mandatory).
DeepTraderX AGENTS.md
Instructions for armandcismaru/DeepTraderX, covering agents.md — guidance for ai agents working on deeptraderx, 1. what this project is, 2. how to run & verify, from repo root and expect occasional flaky trials.
DeepTraderX CLAUDE.md
Instructions for armandcismaru/DeepTraderX, covering claude.md, quick reference and things to remember (high-signal).
zero-to-ai snyk_rules.instructions.md
Snyk Security At Inception.
omni-lpr AGENTS.md
Instructions for habedi/omni-lpr, covering agents.md, mission, core rules, writing style and repository layout.
skills AGENTS.md
AGENTS.md instructions for ultralytics/skills, covering agents.md, core principles (critical), pr workflow, commands and architecture.