onnxtools: Instructions file for Claude Code

CLAUDE.md

onnxtools CLAUDE.md is an instructions file for Claude Code from yyq19990828/onnxtools. It costs 2,819 tokens per session, scanned A, original, MIT.

A navigation and conventions guide for ONNX-based vehicle and licence-plate recognition software. ONNX is a format for sharing machine-learning models between tools; this guide points developers to the relevant code, model, tracking, evaluation, configuration, and testing documentation.

In plain words
What is it for?
Use it when adding model architectures, working on inference or tracking, customising visual output, evaluating results, debugging ONNX or TensorRT builds, changing configuration, or writing tests.
Why use it?
It reduces the time spent searching a large toolkit and helps changes follow the project’s existing design rules. It also shows where different types of work are documented.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is yyq19990828/onnxtools's own configuration. It tells Claude Code how to work on onnxtools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything onnxtools configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yyq19990828/onnxtools. 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/yyq19990828/onnxtools/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/yyq19990828/onnxtools

Made for: Claude Code.

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 onnxtools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yyq19990828/onnxtools/claude-md/github.svg)](https://agentmods.dev/instructions/yyq19990828/onnxtools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yyq19990828/onnxtools/claude-md"><img src="https://agentmods.dev/badge/instructions/yyq19990828/onnxtools/claude-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.

agentmods 80×15 button for onnxtools CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yyq19990828/onnxtools/claude-md"><img src="https://agentmods.dev/badge/instructions/yyq19990828/onnxtools/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,819 This file is loaded in full into every session.
When invoked 2,819 The same file — it is already loaded in full.
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 $0.02819 $0.02819
Opus 5 $0.01409 $0.01409
Sonnet 5 $0.00564 $0.00564
Haiku 4.5 $0.00282 $0.00282

Measured 9d ago against content hash 1dfb3586187d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

onnxtools CLAUDE.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 9d 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.

CLAUDE.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Navigation and conventions file for AI assistants working in this repo. For user-facing install/CLI/perf, see README.md.

ONNX-based vehicle and license plate recognition toolkit. Supports YOLO / RT-DETR / RF-DETR detection, OCR, and color/layer classification.

Quick Navigation

I want to... Go here
Install, run, CLI args, performance numbers README.md
Add a new model architecture Core Conventions below + onnxtools/infer_onnx/CLAUDE.md
Inference engine internals (BaseORT, Result, ORT subclasses) onnxtools/infer_onnx/CLAUDE.md
Visualization customization (13 annotators, 5 presets) onnxtools/utils/CLAUDE.md · docs/annotator_usage.md
Model evaluation (COCO mAP, OCR metrics, MOT HOTA/MOTA/IDF1) onnxtools/eval/CLAUDE.md · docs/evaluation_guide.md
2D multi-object tracking (ByteTrack, OC-SORT) onnxtools/tracking/CLAUDE.md · docs/api/tracking.md
TensorRT build / ONNX debugging tools/README.md · docs/polygraphy使用指南/
Run/write tests tests/CLAUDE.md
Config files (det_config / plate / visualization presets) configs/CLAUDE.md
MCP server / LLM tool interface mcp_tools/CLAUDE.md

Module Index

Path Responsibility Docs
onnxtools/ Core Python package, public API entry CLAUDE.md
onnxtools/infer_onnx/ YOLO / RT-DETR / RF-DETR / OCR inference classes CLAUDE.md
onnxtools/utils/ Image processing, Supervision visualization, OCR metrics CLAUDE.md
onnxtools/eval/ COCO / OCR dataset evaluators CLAUDE.md
onnxtools/tracking/ 2D MOT — ByteTrack (supervision / native) + OC-SORT CLAUDE.md
tools/ Evaluation, TensorRT build, ONNX vs TRT comparison README.md
tests/ unit / integration / contract / performance CLAUDE.md
configs/ Detection classes, OCR dict, visualization presets (YAML) CLAUDE.md
models/ ONNX models and TensorRT engines (.gitignore) CLAUDE.md
specs/ Completed feature specs (spec-kit) CLAUDE.md
openspec/ OpenSpec change proposals and archive CLAUDE.md
docs/ User docs, Polygraphy guide, API reference CLAUDE.md
third_party/ Ultralytics / Polygraphy / RF-DETR integrations CLAUDE.md
mcp_tools/ FastMCP server, LLM tool interface CLAUDE.md
examples/ Demo scripts (demo_pipeline, demo_crop)

Read the full file on GitHub · 178 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. 9d ago First seen · 178 lines · 2,819 tokens per session scan A 1dfb3586187d

Subscribe to this mod's changes

onnxtools CLAUDE.md is an instructions file published in the GitHub repository yyq19990828/onnxtools (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,819 tokens to every session, about $0.0141 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens