geoextractor AGENTS.md

geoextractor AGENTS.md is an instructions file for Codex, OpenCode from Navdeep0p/geoextractor. It costs 445 tokens per session, scanned A, original, MIT.

Project instructions for Geo Extractor, a web app that reads location data from image metadata and displays it on a map. When that metadata is missing, it can estimate a location from visual clues through a serverless service and a vision model.

In plain words
What is it for?
Working on image metadata extraction, map coordinates, fallback location estimation, Supabase Edge Functions, database and error handling, Groq API calls, React interfaces, and Tailwind styling.
Why use it?
They explain who owns each part of the system, which technologies it uses, and how image data moves from the browser to the backend. This gives coding agents the context needed to change the right layer safely.

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/navdeep0p/geoextractor/agents-md
Clone the repo
git clone --depth 1 https://github.com/Navdeep0p/geoextractor

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 geoextractor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/navdeep0p/geoextractor/agents-md.svg)](https://agentmods.dev/instructions/navdeep0p/geoextractor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/navdeep0p/geoextractor/agents-md"><img src="https://agentmods.dev/badge/instructions/navdeep0p/geoextractor/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 445 This file is loaded in full into every session.
When invoked 445 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 5.1 $0.00445 $0.00445
Opus 5 $0.00222 $0.00222
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00044 $0.00044

Measured 5d ago against content hash de082b5c01bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

geoextractor 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 5d 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 · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

"""# AGENTS.md - Context & System Rules for AI Coding Partners

Welcome, agent! You are collaborating on Geo Extractor, a lightweight, high-fidelity web application designed to extract EXIF metadata from uploaded images to plot their coordinates on an interactive map. If the EXIF data is missing or stripped, the application triggers a serverless fallback pipeline that passes the image payload to a vision LLM to estimate the location based on visual landmarks, architectural styles, topography, flora, and environmental clues.


👥 1. The Team & Roles

  • User (Lead Backend Engineer): Responsible for Supabase architecture, Edge Functions, database schema, data models, error handling, and Groq API orchestration.
  • Teammate (Frontend Engineer): Responsible for building the UI canvas using Google Stitch to generate high-fidelity React + Tailwind CSS components.

🛠️ 2. Tech Stack & Infrastructure Environment

  • Frontend Ecosystem: React, Tailwind CSS. Design system, responsive grids, and layout tokens are derived directly from Google Stitch visual blueprints.
  • Client-Side Metadata Parsing: exifreader (or vanilla JS equivalent) executed inside the browser to parse local files before server upload.
  • Backend Runtime: Supabase Edge Functions executing on a Deno (TypeScript) runtime environment.
  • Core AI Inference: Groq Cloud Vision API using highly accelerated models like qwen-2.5-vl-72b or llama-3.2-11b-vision-preview.

🔌 3. The Core API Contract

All code modifications to the backend proxy layers or frontend state consumers must strictly adhere to this exact JSON data handshake. Do not modify key naming conventions, text casing, or structural nestings, as doing so will break the integration between the Google Stitch frontend and the Supabase backend.

3.1. Inbound Request (Frontend ──► Supabase Edge Function)

Sent over HTTP POST only when client-side EXIF processing fails to find GPS metadata. The raw image is passed as a Base64 data string payload.

Read the full file on GitHub · 29 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. 5d ago First seen · 29 lines · 445 tokens per session scan A de082b5c01bb

Subscribe to this mod's changes

geoextractor AGENTS.md is an instructions file published in the GitHub repository Navdeep0p/geoextractor (5 stars, last pushed 22d ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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

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 · 5,182 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

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.

github/spec-kit · 7,104 tokens

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

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

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