What is kura CLAUDE.md?

Repository instructions for Kura, a Next.js application that turns a YouTube video URL into a structured Markdown note. They describe its commands, tests, database work, authentication, and request flow.

Use them when developing, testing, linting, building, or changing Kura’s YouTube transcript, summary, authentication, or database features.

They give the coding agent the project’s working rules and architecture, reducing mistakes when changing the video-summary pipeline or database.

How zhashkevych/kura configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zhashkevych/kura. 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/zhashkevych/kura/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zhashkevych/kura

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/zhashkevych/kura/claude-md/github.svg)](https://agentmods.dev/instructions/zhashkevych/kura/claude-md)

Your own site

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

Per session 1,419 This file is loaded in full into every session.

When invoked 1,419 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	$0.01419	$0.01419
Opus 5	$0.00709	$0.00709
Sonnet 5	$0.00284	$0.00284
Haiku 4.5	$0.00142	$0.00142

Measured 9d ago against content hash f5a1aa2898b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kura 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 9d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Common commands

npm run dev              # Next.js dev server on :3000
npm run build            # Production build
npm run typecheck        # tsc --noEmit (strict)
npm test                 # vitest run (one-shot)
npm run test:watch       # vitest watch mode
npm run lint             # next lint

npm run db:generate      # Generate SQL migration from schema changes
npm run db:push          # Apply schema to Neon directly (no migration file)
npm run db:migrate       # Apply generated migrations
npm run db:seed          # Insert the 3 system templates (src/db/seed.ts)

Run a single test file: npx vitest run src/lib/youtube.test.ts.

Ad-hoc scripts (require a live .env.local):

npx tsx scripts/test-transcript.ts "<youtube url>"   # Supadata only
npx tsx scripts/test-summary.ts    "<youtube url>"   # full pipeline → LLM

Architecture

Kura turns a YouTube URL into a structured Markdown note. Request flow:

POST /api/summaries (src/app/api/summaries/route.ts) — auth, parse URL, upsert videos stub, dedupe per (userId, videoId), insert summaries row with status: 'pending', schedule processSummary via Next's after() and return summaryId.
processSummary (src/lib/worker/process-summary.ts) runs out-of-band: fetches transcript via Supadata, hard-rejects videos > 2h, calls Gemini, writes content/status: 'ready'. On failure it marks the row failed with a user-facing error.
Client polls GET /api/summaries/[id]; when ready, /app/summaries/[id] renders the content via the template's markdownTemplate (Handlebars).

Because the worker is after() — not a queue — Vercel Fluid Compute must be enabled in prod so the response doesn't cut off background work. There is no retry queue; POST /api/summaries/[id]/retry re-runs processSummary on demand.

This is an open-source, self-host-first app with no billing, no paid tier, and no per-user quota. costUsdCents/token counts are recorded on summaries for operational visibility only — nothing enforces a limit.

Read the full file on GitHub · 78 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.

9d ago First seen · 78 lines · 1,419 tokens per session scan A f5a1aa2898b1

Subscribe to this mod's changes

kura CLAUDE.md is an instructions file published in the GitHub repository zhashkevych/kura (10 stars, last pushed 4mo ago), licensed MIT. It adds 1,419 tokens to every session, about $0.0071 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.

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

kura: Instructions file for Claude Code