Image Matching WebUI is a graphical tool for finding corresponding keypoints between two images with different image-matching algorithms. Users can select local or webcam images, choose an algorithm, and inspect the matching result through a Gradio interface.
Borrowing it
Nothing to install: this file belongs to Vincentqyw/image-matching-webui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Vincentqyw/image-matching-webui/main/CLAUDE.mdgit clone --depth 1 https://github.com/Vincentqyw/image-matching-webuiWrote 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/instructions/vincentqyw/image-matching-webui/claude-md)<a href="https://agentmods.dev/instructions/vincentqyw/image-matching-webui/claude-md"><img src="https://agentmods.dev/badge/instructions/vincentqyw/image-matching-webui/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.
<a href="https://agentmods.dev/instructions/vincentqyw/image-matching-webui/claude-md"><img src="https://agentmods.dev/badge/instructions/vincentqyw/image-matching-webui/claude-md.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 | $0.02033 | $0.02033 |
| Opus 5 | $0.01017 | $0.01017 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
image-matching-webui 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Common Commands
# Install from source
conda env create -f environment.yaml && conda activate imcui
pip install -e .
# Run the WebUI (default: http://localhost:7860)
imcui # package CLI
python app.py # direct script
imcui -s 127.0.0.1 -p 8080 # custom host/port
# Lint and format
pre-commit run -a # Run all hooks (ruff, mypy, yaml-check, etc.)
# Run tests
python -m pytest tests/ -s
python -m pytest tests/test_basic.py -s # single test file
# Docker
docker-compose up webui # Web UI service
docker-compose up -d webui # Background
docker-compose build webui # Rebuild
# Git submodules
git submodule update --init --recursive # clone all
git submodule update --remote <path> # update one
Architecture
This is a Gradio WebUI for image matching built on a modified Hierarchical-Localization (hloc) framework. The core pattern: extractors detect keypoints+descriptors from images, matchers pair them. Dense matchers bypass extraction and operate directly on images.
Directory layout
imcui/
hloc/ # Core engine (forked from cvg/Hierarchical-Localization)
extractors/ # Keypoint detector + descriptor models (ALIKED, DISK, SuperPoint, RaCo…)
matchers/ # Matching models (LightGlue, LoFTR, RoMa, SuperGlue, LoMa…)
configs/
extractors.py # confs dict: maps extractor config names → model+preprocessing
matchers.py # confs dict: maps matcher config names → model+preprocessing
pipelines/ # SfM reconstruction pipelines (unused by WebUI)
utils/base_model.py # BaseModel ABC: all models inherit _init / _forward pattern
ui/
app_class.py # Gradio UI definition (ImageMatchingApp, AppSfmUI)
utils.py # run_matching pipeline, RANSAC, visualization, model loading
modelcache.py # ARCSizeAwareModelCache: GPU/CPU memory-aware model LRU cache
cli/main.py # Click CLI entry point (the `imcui` command)
config/app.yaml # Package default config — declarative matcher zoo registry
third_party/ # Git submodules (30+ upstream repos)
config/app.yaml # User-facing config (mirrors the package default)
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.
- 9d ago First seen · 182 lines · 2,033 tokens per session scan A 666f5ca187bb
image-matching-webui CLAUDE.md is an instructions file published in the GitHub repository Vincentqyw/image-matching-webui (1,301 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,033 tokens to every session, about $0.0102 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.
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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.