What is video-research-mcp CLAUDE.md?

A project instruction file for a monorepo, which is one repository containing several related packages, including video research and explainer services.

It guides development, testing, configuration, and commands for video analysis, academic research, content extraction, web search, and explainer-video tools.

It gives the agent shared rules and setup details for working across the services without importing conflicting instructions.

How Galbaz1/video-research-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Galbaz1/video-research-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/Galbaz1/video-research-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Galbaz1/video-research-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/galbaz1/video-research-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/galbaz1/video-research-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/galbaz1/video-research-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/galbaz1/video-research-mcp/claude-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/galbaz1/video-research-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/galbaz1/video-research-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,634 This file is loaded in full into every session.

When invoked 4,634 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	$0.04634	$0.04634
Opus 5	$0.02317	$0.02317
Sonnet 5	$0.00927	$0.00927
Haiku 4.5	$0.00463	$0.00463

Measured 10d ago against content hash b70c7594b4af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-research-mcp 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 10d 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 · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Memory Source Guard

Do not import AGENTS.md (for example via @AGENTS.md or @../AGENTS.md) from this file or any .claude/rules/*.md file. AGENTS.md is Codex-specific and keeping it out of Claude memory prevents duplicate or conflicting guidance.

What This Is

A monorepo with three MCP servers (51 tools total):

video-research-mcp (root) — 34 tools for video analysis, deep research, academic papers, content extraction, web search, and context caching. Powered by Gemini 3.1 Pro (google-genai SDK) and YouTube Data API v3.
video-explainer-mcp (packages/video-explainer-mcp/) — 15 tools for synthesizing explainer videos from research content. Wraps the video_explainer CLI.
video-agent-mcp (packages/video-agent-mcp/) — 2 tools providing an autonomous research agent orchestrator. Wraps video-research-mcp tools with planning and execution loops.

All servers share ~/.config/video-research-mcp/.env for configuration. Built with Pydantic v2, hatchling. Python >= 3.11.

Commands

# video-research-mcp (root)
uv venv && source .venv/bin/activate && uv pip install -e ".[dev]"  # install
uv run pytest tests/ -v                                              # all tests
uv run ruff check src/ tests/                                        # lint
GEMINI_API_KEY=... uv run video-research-mcp                         # run server

# video-explainer-mcp (packages/)
cd packages/video-explainer-mcp
uv venv && source .venv/bin/activate && uv pip install -e ".[dev]"  # install
uv run pytest tests/ -v                                              # all tests
uv run ruff check src/ tests/                                        # lint
EXPLAINER_PATH=/path/to/video_explainer uv run video-explainer-mcp  # run server

python3 ~/.claude/scripts/detect_review_scope.py --json               # auto-select review scope

Automated Review Triggers

Use scripts/detect_review_scope.py --json to choose the review mode from git state:

Read the full file on GitHub · 283 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.

10d ago First seen · 283 lines · 4,634 tokens per session scan A b70c7594b4af

Subscribe to this mod's changes

video-research-mcp CLAUDE.md is an instructions file published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 4,634 tokens to every session, about $0.0232 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 Code ai-tools gemini mcp mcp-server

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

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 · 5,153 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

video-research-mcp: Instructions file for Claude Code