agentmods.dev

eyeroll: Instructions file for Claude Code

CLAUDE.md

eyeroll CLAUDE.md is an instructions file for Claude Code from mnvsk97/eyeroll. It costs 901 tokens per session, scanned A, original, MIT.

A tool that watches online or local video and turns what it sees into structured notes for coding agents. It can use several hosted or local AI models to analyze the footage.

In plain words
What is it for?
Use it to analyze Loom or YouTube links, local videos, or screenshots and produce notes that an agent can use for coding work.
Why use it?
It saves developers from manually reviewing long recordings when they need to understand a bug, feature request, or other visual information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is mnvsk97/eyeroll's own configuration. It tells Claude Code how to work on eyeroll itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eyeroll configures →

not rated 17repo 3mo ago A scan 901 tokens original MIT
View source ↗ mnvsk97/eyeroll mnvsk97.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to mnvsk97/eyeroll. 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/mnvsk97/eyeroll/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mnvsk97/eyeroll

Made for: Claude Code.

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 eyeroll CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mnvsk97/eyeroll/claude-md.svg)](https://agentmods.dev/instructions/mnvsk97/eyeroll/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mnvsk97/eyeroll/claude-md"><img src="https://agentmods.dev/badge/instructions/mnvsk97/eyeroll/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 901 This file is loaded in full into every session.
When invoked 901 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00901 $0.00901
Opus 5 $0.00451 $0.00451
Sonnet 5 $0.00180 $0.00180
Haiku 4.5 $0.00090 $0.00090

Measured 8d ago against content hash 3104ecb416c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

eyeroll CLAUDE.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.

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project

eyeroll — AI eyes that roll through video footage. Takes video URLs (Loom, YouTube), local video files, or screenshots as input. Supports Gemini 2.5 Flash (default), OpenAI GPT-4o, Ollama (local), OpenRouter, Groq, Grok, Cerebras, and any OpenAI-compatible endpoint. Produces structured notes that coding agents can act on — fix bugs, build features, create skills, or anything else.

Commands

# Install
pip install .
# or with uv:
uv sync

# Run tests
pytest
pytest --cov --cov-report=term-missing

# CLI
eyeroll init                                              # set up Gemini API key
eyeroll watch <url-or-path>                               # analyze (gemini default)
eyeroll watch <url> --context "broken after PR #432"      # with context
eyeroll watch <path> --backend ollama                     # use local Qwen3-VL
eyeroll watch <path> -b ollama -m qwen3-vl:2b             # specific model
eyeroll watch <path> --verbose --output report.md         # verbose + write to file

Architecture

  • Pipeline: acquire.py → extract.py → analyze.py → watch.py (orchestrator)
  • backend.py: Abstract Backend class with GeminiBackend and OllamaBackend implementations. Factory via get_backend().
  • acquire.py: Downloads from URLs via yt-dlp, resolves local files. Returns file_path, media_type, title.
  • extract.py: ffmpeg wrappers for key frame extraction, audio extraction, duration detection.
  • analyze.py: Backend-agnostic analysis. Frame-by-frame with structured prompts, direct video upload (Gemini only), audio transcription, and synthesis.
  • watch.py: Orchestrates the pipeline. Chooses strategy based on backend capabilities and video size.
  • context.py: Auto-discovers codebase context from CLAUDE.md, AGENTS.md, CURSOR.md, and similar files.
  • cost.py: Cost estimation for API calls. Prints token counts and USD cost after each run.
  • cli.py: Click CLI with init and watch commands. Flags include --backend, --model, --no-context, --no-cost, --min-audio-confidence, --scene-threshold.

Read the full file on GitHub · 63 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. 8d ago First seen · 63 lines · 901 tokens per session scan A 3104ecb416c1

Subscribe to this mod's changes

eyeroll CLAUDE.md is an instructions file published in the GitHub repository mnvsk97/eyeroll (17 stars, last pushed 3mo ago), licensed MIT. It adds 901 tokens to every session, about $0.0045 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 2026-08-30.

Claude CodeResearchagent-skillsaibug-reportdeveloper-toolsgemini
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

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

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