What is blur-studio AGENTS.md?

Instructions for using Blur Studio, a coordinate-based image tool that applies Gaussian blur with feathered edges to selected ellipses or rectangles.

Guiding agents that blur or redact parts of photos and screenshots, such as faces, license plates, screens, or documents, by supplying normalized image coordinates.

They prevent an agent from assuming the tool can find faces or objects automatically, and explain how to keep excluded areas sharp.

How fauzulkc/blur-studio configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to fauzulkc/blur-studio. 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/fauzulkc/blur-studio/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fauzulkc/blur-studio

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/fauzulkc/blur-studio/agents-md/github.svg)](https://agentmods.dev/instructions/fauzulkc/blur-studio/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fauzulkc/blur-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/fauzulkc/blur-studio/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fauzulkc/blur-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/fauzulkc/blur-studio/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,246 This file is loaded in full into every session.

When invoked 5,246 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.05246	$0.05246
Opus 5.5	$0.02098	$0.02098
Sonnet 5.5	$0.01049	$0.01049
Haiku 4.5	$0.00525	$0.00525

Measured 2mo ago against content hash 9c0b98a86d75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blur-studio AGENTS.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

file containing that JSON (curl's `@file` idiom) — use `@file.json` for

AGENTS.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Blur Studio

This file gives any AI coding agent (Claude Code, Cursor, OpenAI Codex CLI, Gemini CLI/Antigravity, Amp, or a plain shell-driven agent) everything needed to operate this tool correctly — not just read its code. It stands on its own: you do not need .claude/skills/blur-studio/SKILL.md (a Claude-specific packaged skill covering the same ground) to use anything described here.

Repo: https://github.com/fauzulkc/blur-studio · License: MIT · Author: Fauzul Chowdhury.

What this repo is

Blur Studio is a coordinate-based selective image blurring tool: give it normalized 0-1 regions of an image (ellipses or rectangles) and it applies Gaussian blur with a feathered edge inside those regions, optionally protecting other regions ("exclusions") so they stay 100% sharp even if a blur region overlaps them. It ships three parallel entry points into the same business logic (blurService.js):

cli.js — a commander-based CLI, installed as the blur-studio bin.
mcp-server.js — an MCP server (@modelcontextprotocol/sdk, STDIO transport) registered in .mcp.json under the name blur-studio.
server.js — an Express HTTP API (default port 3333, override via the PORT env var) that the React/Vite web UI (src/) talks to.

All three are thin wrappers: they parse their respective input format, call the same functions exported from blurService.js, and format the result. blurService.js itself shells out to blur_processor.py (Pillow + numpy) to do the actual pixel work via spawn('python3', [...]).

THE load-bearing fact: no auto-detection

This tool does not detect faces, license plates, screens, or any other subject. It has no computer-vision model of any kind — it is a coordinate-in, blurred-pixels-out compositor. There is no "auto-blur faces" mode, no --detect flag, nothing.

If you are an agent being asked to blur faces/plates/screens/etc. in a photo, you must look at the image with your own vision, decide what needs obscuring, and supply the exact normalized coordinates of those regions yourself. Skipping this and guessing coordinates, or hoping the tool infers them, will blur the wrong region, blur nothing, or blur the whole image. Always view the image (read it as an image input, not just a file listing) before constructing any targets/exclusions array.

Read the full file on GitHub · 371 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.

2mo ago First seen · 371 lines · 5,246 tokens per session scan A 9c0b98a86d75

Subscribe to this mod's changes

blur-studio AGENTS.md is an instructions file published in the GitHub repository fauzulkc/blur-studio (0 stars, last pushed 7d ago), licensed MIT. It adds 5,246 tokens to every session, about $0.0210 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media

blur-studio AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
blur-studio AGENTS.mdfauzulkc/blur-studio	Instructions file	0	7d ago	MIT	A	5,246	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

blur-studio: Instructions file for Codex