What is mlx-porting-skill AGENTS.md?

Contributor instructions for a repository that ports machine-learning models to MLX, Apple's framework for running machine learning on Apple hardware. They define research, validation, benchmarking, and safety expectations.

Use them when adding MLX porting work, reviewing research-based recommendations, writing skills or scripts, and validating optimization changes.

They help prevent unverified techniques, unsupported claims, unsafe remote code execution, and optimization changes without rollback or correctness checks.

How Amal-David/mlx-porting-skill configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Amal-David/mlx-porting-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Amal-David/mlx-porting-skill/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Amal-David/mlx-porting-skill

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/amal-david/mlx-porting-skill/agents-md/github.svg)](https://agentmods.dev/instructions/amal-david/mlx-porting-skill/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/amal-david/mlx-porting-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/amal-david/mlx-porting-skill/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amal-david/mlx-porting-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/amal-david/mlx-porting-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 713 This file is loaded in full into every session.

When invoked 713 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00713	$0.00713
Opus 5.5	$0.00285	$0.00285
Sonnet 5.5	$0.00143	$0.00143
Haiku 4.5	$0.00071	$0.00071

Measured 2mo ago against content hash 4d59e8ddb6eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mlx-porting-skill AGENTS.md scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mlx-porting-skill CLAUDE.md — 88% identical, 12 lines differ

AGENTS.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributor instructions

Treat this repository as an executable engineering standard, not a prompt collection.

Preserve source provenance and review depth. Never promote an indexed source to synthesized without recording the affected rule or runbook.
Prefer official MLX code and documentation over secondary performance claims.
Do not introduce a technique as “supported” until a reproducible MLX path and validation gate exist.
Keep SKILL.md compact. Put architecture detail in references/ and structured facts in assets/.
Scripts must be inspectable, non-destructive by default, and must not execute remote model code.
Daily automation may collect candidates and open a review change. It must not auto-merge research-derived recommendations.
Every optimization change needs a correctness check, benchmark metadata, and a rollback condition.

Optional Superplan Operating Contract

When Superplan is installed, load and follow superplan-entry from the first available location:

.codex/skills/superplan-entry/SKILL.md
.superplan/skills/superplan-entry/SKILL.md
${HOME}/.config/superplan/skills/superplan-entry/SKILL.md
${HOME}/.codex/skills/superplan-entry/SKILL.md

If Superplan is unavailable, continue with the repository-native workflow in VALIDATION.md; optional orchestration must never make a fresh checkout unusable.

When Superplan is active:

No implementation before loading and following superplan-entry.
No broad repo exploration before loading and following superplan-entry.
No planning or repo-specific clarification before loading and following superplan-entry.
Keep workflow control internal: do not narrate skill names, routing, or command logs to the user.
If .superplan/ exists, treat the Superplan CLI as the execution control plane.
Prefer workspace harnesses, scripts, and custom workflows when superplan-entry routes you there.

Canonical loop when Superplan is active:

Run superplan status --json.
Claim or resume work with superplan run --json or superplan run <task_id> --json.
Continue through the owning Superplan phase instead of improvising a parallel workflow.
Use lifecycle commands such as superplan task runtime block, superplan task runtime request-feedback, and superplan task review complete; never hand-edit .superplan/runtime/.

Read the full file on GitHub · 54 lines

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.

2mo ago First seen · 54 lines · 713 tokens per session scan C 4d59e8ddb6eb

Subscribe to this mod's changes

mlx-porting-skill AGENTS.md is an instructions file published in the GitHub repository Amal-David/mlx-porting-skill (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 713 tokens to every session, about $0.0029 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Apple Silicon Data and AI LLM agent-skill benchmarking machine-learning mlx

mlx-porting-skill AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mlx-porting-skill AGENTS.mdAmal-David/mlx-porting-skill	Instructions file	5	yesterday	Apache-2.0	C	713	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mlx-porting-skill: Instructions file for Codex