onnx2coreml AGENTS.md

onnx2coreml AGENTS.md is an instructions file for Codex, OpenCode from devin-lai/onnx2coreml. It costs 831 tokens per session, scanned A, original, BSD-3-Clause.

Repository instructions for contributors to onnx2coreml, a tool that converts ONNX machine-learning models into Apple Core ML model files.

In plain words
What is it for?
Use it when adding support for an ONNX operator, changing conversion behavior, or writing related tests.
Why use it?
It explains the converter's pipeline and code boundaries, helping changes stay consistent and testable.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/devin-lai/onnx2coreml/agents-md
Clone the repo
git clone --depth 1 https://github.com/devin-lai/onnx2coreml

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.

agentmods badge for onnx2coreml AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/devin-lai/onnx2coreml/agents-md.svg)](https://agentmods.dev/instructions/devin-lai/onnx2coreml/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/devin-lai/onnx2coreml/agents-md"><img src="https://agentmods.dev/badge/instructions/devin-lai/onnx2coreml/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 831 This file is loaded in full into every session.
When invoked 831 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00831 $0.00831
Opus 5 $0.00415 $0.00415
Sonnet 5 $0.00166 $0.00166
Haiku 4.5 $0.00083 $0.00083

Measured 4d ago against content hash e9173382e2b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onnx2coreml 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 4d 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.

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer guide for onnx2coreml

Guidance for contributors working in this repo. Keep changes surgical, tested, and consistent with the patterns below.

What this is

An ONNX → Core ML converter producing .mlpackage (ML Program / MIL) and .mlmodel (NeuralNetwork), built on top of coremltools' MIL builder.

Architecture (one pass through the pipeline)

ONNX → _io.load → _passes.run → _fusion.run → coverage-gate → Converter.to_mil
     → _backend.program_to_mlmodel → MLModel (.mlpackage / .mlmodel) → _verify
  • _mil.py and _backend.py are the only modules that import coremltools. Keep it that way — this is how the project stays maintainable as Core ML evolves.
  • converter.py orchestrates: coverage gate, then a topological walk emitting MIL ops.
  • _target.py maps deployment-target/format/precision strings to coremltools enums. The MIL function is authored at iOS17 for .mlpackage and iOS15 for .mlmodel (the NeuralNetwork backend rejects newer opsets).

Adding an operator lowering

  1. Pick the right family module under src/onnx2coreml/_lowering/ (e.g. _conv.py).
  2. Write def lower(ctx, node) -> Var | list[Var]: — read inputs via operands(ctx.values_map, node, [...]), emit mb.* ops, and name the final op for each output with name=node.output[i] (so Core ML's predicted output keys match ONNX names). Never pass name=None to an intermediate op — omit the kwarg.
  3. Add the op key to that module's REGISTRY dict. Keys are unique across modules (a duplicate raises at import).
  4. Find the exact MIL op + parameter names in ../coremltools/coremltools/converters/mil/mil/ops/defs/ — do not guess.
  5. Add a parity test in tests/test_ops_<family>.py parametrized over fmt in ["mlpackage", "mlmodel"].

Helpers in _lowering/_common.py: binary(mb_op), unary(mb_op), const_array(ctx, node, idx), get_attr, operands.

Testing

.venv/bin/python -m pytest tests/ -q          # full suite
.venv/bin/python -m pytest tests/test_ops_conv.py -q

Read the full file on GitHub · 66 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.

  1. 4d ago First seen · 66 lines · 831 tokens per session scan A e9173382e2b8

Subscribe to this mod's changes

onnx2coreml AGENTS.md is an instructions file published in the GitHub repository devin-lai/onnx2coreml (153 stars, last pushed 2mo ago), licensed BSD-3-Clause. It adds 831 tokens to every session, about $0.0042 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.

Related

Other instructions, from other repositories

speech-swift copilot-instructions.md

Copilot instructions for soniqo/speech-swift, a project described as: AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML.

soniqo/speech-swift · 4 tokens

speech-swift CLAUDE.md

Claude Code instructions for soniqo/speech-swift, a project described as: AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML.

soniqo/speech-swift · 3 tokens

speech-swift AGENTS.md

AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.

soniqo/speech-swift · 5,053 tokens

kesha-voice-kit AGENTS.md

AGENTS.md instructions for drakulavich/kesha-voice-kit: Project rules, build commands, release process, and lessons learned live in CLAUDE.md — single source of truth for every coding agent (Claude Code, Cursor, Aider, Codex, etc.). When CLAUDE.md and any other doc disagree, CLAUDE.md wins.

drakulavich/kesha-voice-kit · 70 tokens

coreai-model-zoo AGENTS.md

AGENTS.md instructions for john-rocky/coreai-model-zoo, covering agents.md — for coding agents porting a model to core ai, the one thing to understand before you start, route, decide whether to port at all and the two gates a port must pass.

john-rocky/coreai-model-zoo · 1,998 tokens

kesha-voice-kit CLAUDE.md

Claude Code instructions for drakulavich/kesha-voice-kit, covering claude.md, project overview, critical development rules, default tts voices must be male and never auto-download the engine or models.

drakulavich/kesha-voice-kit · 5,750 tokens