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.
npx agentmods add instructions/fauzulkc/blur-studio/agents-mdgit clone --depth 1 https://github.com/fauzulkc/blur-studioWrote 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/fauzulkc/blur-studio/agents-md)<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="Measured on agentmods" 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 | $0.05246 | $0.05246 |
| Opus 5 | $0.02623 | $0.02623 |
| Sonnet 5 | $0.01049 | $0.01049 |
| Haiku 4.5 | $0.00525 | $0.00525 |
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 3d 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 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— acommander-based CLI, installed as theblur-studiobin.mcp-server.js— an MCP server (@modelcontextprotocol/sdk, STDIO transport) registered in.mcp.jsonunder the nameblur-studio.server.js— an Express HTTP API (default port3333, override via thePORTenv 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.
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.
- 3d ago First seen · 371 lines · 5,246 tokens per session scan A 9c0b98a86d75
blur-studio AGENTS.md is an instructions file published in the GitHub repository fauzulkc/blur-studio (0 stars, last pushed yesterday), licensed MIT. It adds 5,246 tokens to every session, about $0.0262 per session on Opus 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.
Other instructions, from other repositories
linkedin-content-engine CLAUDE.md
Claude Code instructions for mdbailin/linkedin-content-engine, covering claude implementation brief, goal, architecture constraints, required mcp tools and readbrandprofile.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.
ukulele-companion CLAUDE.md
Claude Code instructions for baijum/ukulele-companion, a project described as: An offline app for learning ukulele — on Android and iOS. Chords, scales, music theory, composition tools, and more.
sound-effects-mcp CLAUDE.md
Claude Code instructions for sawa-zen/sound-effects-mcp, covering claude.md, プロジェクト概要, よく使うコマンド, 開発 and テスト.