Borrowing it
Nothing to install: this file belongs to ygq-future/openai-vision-mcp-server. 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/ygq-future/openai-vision-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/ygq-future/openai-vision-mcp-serverWrote 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/ygq-future/openai-vision-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/ygq-future/openai-vision-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ygq-future/openai-vision-mcp-server/agents-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/ygq-future/openai-vision-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ygq-future/openai-vision-mcp-server/agents-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 | $0.00850 | $0.00850 |
| Opus 5 | $0.00425 | $0.00425 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
openai-vision-mcp-server 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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Project purpose
Build openai-vision-mcp-server, a local stdio MCP server that accepts images from file:// URIs, HTTP(S) URLs, or Base64, preprocesses them, and analyzes them through an OpenAI Chat Completions-compatible vision endpoint.
Fixed product decisions
- Support only the OpenAI Chat Completions-compatible request and response format.
- Do not add Anthropic support, provider switching, a provider interface, or a generic adapter layer.
- Run as a local stdio MCP server and publish an executable npm package for
npxusage. - Read provider configuration only from the MCP client's per-server environment variables.
- Keep stdout exclusively for MCP JSON-RPC messages. Send diagnostics to stderr and never log credentials or Base64 payloads.
- Store project documentation and plans under
docs/. This directory is intentionally ignored by Git.
Runtime and package management
- Use TypeScript with strict type checking and ESM output.
- Support Node.js 20.19.0 or newer.
- Use Bun for dependency installation, scripts, tests, packing, and publishing.
- Commit
bun.lock; do not generate npm, pnpm, or Yarn lockfiles. - Prefer Node.js built-ins and native
fetch. Do not add the OpenAI SDK unless a future requirement cannot be met by the fixed Chat Completions HTTP contract.
Required formatting
Prettier must use exactly:
{
"singleQuote": true,
"semi": false,
"trailingComma": "all",
"printWidth": 120,
"tabWidth": 2,
"arrowParens": "avoid",
"endOfLine": "lf",
"bracketSpacing": true,
"bracketSameLine": true
}
Use ESLint flat configuration with type-aware TypeScript rules. Do not disable a rule inline unless the comment explains the concrete reason.
Architecture constraints
- Keep image acquisition, validation, normalization, tiling, API calls, aggregation, and MCP transport in separate focused modules.
- Decode each source once. Generate the overview and detail tiles from the decoded original, never from an already compressed derivative.
- Do not claim to know semantic content before the first vision call. Overview planning may propose regions; uncertain results must fall back to deterministic overlapping grid coverage.
- Treat
maxTilesas a hard per-call ceiling on detail tiles. The overview does not count toward it. - Preserve tile and batch order explicitly. Never rely on promise completion order.
- When a budget prevents complete coverage, return
complete: falsewith a machine-readable warning; never silently imply complete analysis. - Apply configured allowed-root and SSRF policies on every local-file or remote fetch. The current defaults are permissive; documentation must explain how users opt into root restrictions and public-network-only URL access. Redirect limits, timeouts, byte limits, and decoded-pixel limits always remain enforced.
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.
- 8d ago First seen · 71 lines · 850 tokens per session scan A 4f5deaf02ad6
openai-vision-mcp-server AGENTS.md is an instructions file published in the GitHub repository ygq-future/openai-vision-mcp-server (2 stars, last pushed 14d ago), licensed MIT. It adds 850 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 2026-08-31.
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.