videre: Instructions file for Claude Code

CLAUDE.md

videre CLAUDE.md is an instructions file for Claude Code from erhangundogan/videre. It costs 7,993 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for videre, a Rust command-line tool that manages a local media library using one SQLite database. It supports finding duplicates, searching by meaning, and recognizing faces.

In plain words
What is it for?
Use them when developing videre, running its builds and tests, changing commands or shared logic, or updating the user documentation that describes changed behavior.
Why use it?
They help an agent understand how the project is organized and how to investigate changes before modifying shared behavior or documentation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is erhangundogan/videre's own configuration. It tells Claude Code how to work on videre 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 videre configures →

Reuse

Borrowing it

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

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 videre CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/erhangundogan/videre/claude-md.svg)](https://agentmods.dev/instructions/erhangundogan/videre/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/erhangundogan/videre/claude-md"><img src="https://agentmods.dev/badge/instructions/erhangundogan/videre/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,993 This file is loaded in full into every session.
When invoked 7,993 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 $0.07993 $0.07993
Opus 5 $0.03997 $0.03997
Sonnet 5 $0.01599 $0.01599
Haiku 4.5 $0.00799 $0.00799

Measured 2d ago against content hash f747ed0e4560, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

videre 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 2d 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 · 613 lines

How it starts

The opening of the file, as written. The whole thing — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.

videre

A fast Rust CLI for managing a local media library: duplicate detection, semantic search, and face recognition, all around a single SQLite database.

User-facing documentation lives at https://docs.videre.sh, generated from docs/ in this repo. This file is for working on videre, in two parts kept deliberately separate: the working methodology just below (how to work here), then the measured facts (build and test invariants, findings, and traps easy to reintroduce). It is deliberately not a command reference. When you change behaviour, update the relevant page under docs/src/content/docs/ in the same commit.

How to work on videre

Methodology, kept separate from the measured facts that follow. These are working practices, not project truths.

Discovery before spec. For any change touching shared logic, several subcommands, cross-cutting arguments or common behaviour, search code, tests, git history and docs exhaustively first. Ask rather than guess.

Shared code first. The same thing implemented twice is the worst outcome; the second caller triggers extraction and refactoring of the first. Where it lives is the videre-core-versus-shared-module rule under Project structure.

Test first when fixing a bug. Write it, run it, watch it fail. A test that has never failed has not been shown to test anything.

Find the cause before mitigating. cargo test has four target kinds (--lib, --bins, --test, --doc), so tests/ is not the set of tests.

Verify before claiming done. Run the command and read its real output; if tests fail, say so with the output.

Challenge inherited constraints. The model, the schema and the stored data are variables. Ask what recompute cost is acceptable before optimising within assumed limits.

Read the docs before advising. Grep videre's own docs for a flag before recommending a value.

New settings go in config.toml and videre config set, never a new environment variable. Do not design for backwards compatibility; users install latest.

Read the full file on GitHub · 613 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. 2d ago Changed · +6 lines · +145 tokens per session f747ed0e4560
  2. 7d ago First seen · 607 lines · 7,848 tokens per session scan A d87a1b8f634a

Subscribe to this mod's changes

videre CLAUDE.md is an instructions file published in the GitHub repository erhangundogan/videre (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 7,993 tokens to every session, about $0.0400 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.

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