What is vision-bridge-mcp AGENTS.md?

Project instructions for Atlas Vision MCP, a bridge that lets text-only coding agents inspect local images through a vision provider. MCP is a standard way for an AI agent to call external tools; this project returns written and structured image evidence.

Use it to analyze images, read text from them, inspect screenshots or clipboard images, compare images, extract regions, and process image batches.

It lets an agent work with screenshots, photos, and other images when the agent itself mainly handles text.

How QuangThai/vision-bridge-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to QuangThai/vision-bridge-mcp. 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/QuangThai/vision-bridge-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/QuangThai/vision-bridge-mcp

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/quangthai/vision-bridge-mcp/agents-md.svg)](https://agentmods.dev/instructions/quangthai/vision-bridge-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/quangthai/vision-bridge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/quangthai/vision-bridge-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 818 This file is loaded in full into every session.

When invoked 818 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.

Model	Per session	Once invoked
Fable 5.1	$0.00818	$0.00818
Opus 5	$0.00409	$0.00409
Sonnet 5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 7d ago against content hash 6d02d0c5d682, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vision-bridge-mcp 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 7d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions for Atlas Vision MCP

Project Overview

Atlas Vision MCP is an MCP vision bridge for text-only coding agents. It reads local images, calls a dedicated vision provider (OpenAI-compatible), and returns markdown + structured JSON evidence.

Stack: TypeScript, Node.js ≥ 20, pnpm, MCP SDK (stdio), zod, sharp, vitest, tsup, biome
CLI entrypoint: npx atlas-vision-mcp (or atlas-vision doctor, analyze, ocr, compare, serve)
11 MCP tools: should_use_atlas_vision, analyze_image, ocr_image, analyze_clipboard, ocr_clipboard, diagnose_clipboard, analyze_ui_screenshot, analyze_ui_clipboard, compare_images, extract_region, analyze_image_batch
Code: src/ (cli, config, extraction, image, providers, security, tools)
Tests: tests/ — run pnpm vitest run for current count

Quick Checks

pnpm test        # run all tests (vitest)
pnpm typecheck   # tsc --noEmit
pnpm lint        # biome check
pnpm build       # tsup bundle

What's Next

The project roadmap lives at docs/product/roadmap.md — see what's planned for future phases. To propose improvements or report friction, see docs/IMPROVEMENT_PROTOCOL.md. Open backlog items are listed in docs/HARNESS_BACKLOG.md or via harness-cli query backlog --open.

Git & Harness

This repo uses git. Always check git status --short before starting work.
The harness DB is at harness.db (.gitignored). Initialize with scripts/bin/harness-cli init if missing.
After completing a task, record a trace with harness-cli record trace to capture outcomes and friction for future agents.

Registered Tools (harness)

These tools are registered in the harness DB and can be looked up by capability:

Capability	Tool	Command
`build`	pnpm	`pnpm`
`test-runner`	vitest	`pnpm vitest`
`lint`	biome	`pnpm biome`
`typecheck`	typescript	`pnpm tsc`
`bundler`	tsup	`pnpm tsup`

Run harness-cli query tools --capability <name> --status present to check availability before a workflow step.

Read the full file on GitHub · 73 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.

7d ago First seen · 73 lines · 818 tokens per session scan A 6d02d0c5d682

Subscribe to this mod's changes

vision-bridge-mcp AGENTS.md is an instructions file published in the GitHub repository QuangThai/vision-bridge-mcp (10 stars, last pushed 21d ago), licensed MIT. It adds 818 tokens to every session, about $0.0041 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.

Building agents Creative and media

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

vision-bridge-mcp: Instructions file for Codex