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 skills add quattro/jax-numerics-agent --skill jax_equinox_best_practicesgit clone --depth 1 https://github.com/quattro/jax-numerics-agentWrote 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/quattro/jax-numerics-agent/jax_equinox_best_practices)<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.
<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>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 | $0.00035 | $0.02065 |
| Opus 5.5 | $0.00014 | $0.00826 |
| Sonnet 5.5 | $0.00007 | $0.00413 |
| Haiku 4.5 | $0.00003 | $0.00206 |
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 2mo 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 — 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.mdchecklists/jit_static_pytree_checklist.mdchecklists/numerics_ad_testing_checklist.mdchecklists/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.pysnippets/partition_static_state.pysnippets/filter_vmap_batching.pysnippets/prng_split_by_tree.pysnippets/filter_cond_static.pysnippets/linear_operator_pattern.pysnippets/custom_jvp_norm.pysnippets/implicit_jvp.pysnippets/test_jvp_finite_difference.pysnippets/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
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.
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.
- 2mo ago First seen · 199 lines · 35 tokens per session scan A 9a11943b4da6
jax-equinox-numerics is a skill published in the GitHub repository quattro/jax-numerics-agent (9 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 2,065 once invoked, about $0.0001 per session on Opus 5.5. 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
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
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.
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…
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.