agentmods.dev

jax-equinox-numerics

jax-equinox-numerics is a skill for Codex from quattro/jax-numerics-agent. It costs 35 tokens per session (2,065 once invoked), scanned A, original, MIT.

A set of coding practices and checklists for numerical projects built with JAX and Equinox, Python tools for fast mathematical computation and machine learning. It also covers related libraries for linear algebra, optimization, and automatic differentiation.

In plain words
What is it for?
Use it when designing, implementing, or reviewing a JAX and Equinox codebase, especially before and after making changes.
Why use it?
It helps keep numerical code consistent with the repository's style and catches common design, compilation, testing, and math-related problems.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions subagents; mentions Codex.

not rated 9repo 28d ago A scan 35 tokens original MIT

Good fit Use it when designing, implementing, or reviewing a JAX and Equinox codebase, especially before and after making changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/quattro/jax-numerics-agent/jax_equinox_best_practices
View source ↗ quattro/jax-numerics-agent
Install

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.

Any agent
npx skills add quattro/jax-numerics-agent --skill jax_equinox_best_practices
Clone the repo
git clone --depth 1 https://github.com/quattro/jax-numerics-agent

Made for: 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 jax-equinox-numerics

README.md
[![agentmods](https://agentmods.dev/badge/skills/quattro/jax-numerics-agent/jax_equinox_best_practices/github.svg)](https://agentmods.dev/skills/quattro/jax-numerics-agent/jax_equinox_best_practices)
Your own site
<a href="https://agentmods.dev/skills/quattro/jax-numerics-agent/jax_equinox_best_practices"><img src="https://agentmods.dev/badge/skills/quattro/jax-numerics-agent/jax_equinox_best_practices/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 jax-equinox-numerics

Your own site · 80×15
<a href="https://agentmods.dev/skills/quattro/jax-numerics-agent/jax_equinox_best_practices"><img src="https://agentmods.dev/badge/skills/quattro/jax-numerics-agent/jax_equinox_best_practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,065 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 $0.00035 $0.02065
Opus 5 $0.00017 $0.01033
Sonnet 5 $0.00007 $0.00413
Haiku 4.5 $0.00003 $0.00206

Measured 11d ago against content hash 9a11943b4da6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

jax-equinox-numerics 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 11d 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/jax_equinox_best_practices/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JAX + Equinox Best Practices

Guidance for software engineering practices around numerical/JAX codebases using JAX + Equinox + Lineax + Optimistix.

This file is the entrypoint. Keep it lightweight and load focused references for implementation details.

Companion checklists

Apply these checklists when using this skill.

Repo-local paths

  • checklists/jax_equinox_design_checklist.md
  • checklists/jit_static_pytree_checklist.md
  • checklists/numerics_ad_testing_checklist.md
  • checklists/linear_algebra_checklist.md

Global install paths (scripts/install_skills_with_assets.sh)

  • ~/.codex/skills/assets/checklists/jax_equinox_design_checklist.md
  • ~/.codex/skills/assets/checklists/jit_static_pytree_checklist.md
  • ~/.codex/skills/assets/checklists/numerics_ad_testing_checklist.md
  • ~/.codex/skills/assets/checklists/linear_algebra_checklist.md

Checklist workflow

  • Before implementation: open the relevant companion checklist(s) and scope the work against them.
  • During implementation: keep checklist items aligned with code/design decisions.
  • Before completion: re-run the checklist and explicitly document any intentionally unchecked item.

Companion snippets

Use these snippets as implementation starters when they match the task.

Repo-local paths

  • snippets/jit_boundary.py
  • snippets/partition_static_state.py
  • snippets/filter_vmap_batching.py
  • snippets/prng_split_by_tree.py
  • snippets/filter_cond_static.py
  • snippets/linear_operator_pattern.py
  • snippets/custom_jvp_norm.py
  • snippets/implicit_jvp.py
  • snippets/test_jvp_finite_difference.py
  • snippets/abc_module_pattern.py

Global install paths (scripts/install_skills_with_assets.sh)

  • ~/.codex/skills/assets/snippets/jit_boundary.py
  • ~/.codex/skills/assets/snippets/partition_static_state.py
  • ~/.codex/skills/assets/snippets/filter_vmap_batching.py
  • ~/.codex/skills/assets/snippets/prng_split_by_tree.py
  • ~/.codex/skills/assets/snippets/filter_cond_static.py
  • ~/.codex/skills/assets/snippets/linear_operator_pattern.py
  • ~/.codex/skills/assets/snippets/custom_jvp_norm.py
  • ~/.codex/skills/assets/snippets/implicit_jvp.py
  • ~/.codex/skills/assets/snippets/test_jvp_finite_difference.py
  • ~/.codex/skills/assets/snippets/abc_module_pattern.py

Read the full file on GitHub · 199 lines

Files

What ships with it

4 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.

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. 11d ago First seen · 199 lines · 35 tokens per session scan A 9a11943b4da6

Subscribe to this mod's changes

jax-equinox-numerics is a skill published in the GitHub repository quattro/jax-numerics-agent (9 stars, last pushed 28d ago), licensed MIT. It adds 35 tokens to every session and 2,065 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.

LanguagesPythonScientific
Related

Other skills, from other repositories

jupyter-notebook

Iterative Python via live Jupyter kernel (hamelnb).

NousResearch/hermes-agent · 18 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

bioservices

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use…

K-Dense-AI/scientific-agent-skills · 73 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

NVIDIA/skills · 51 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens