hve-video-director: Instructions file for Claude Code

CLAUDE.md

hve-video-director CLAUDE.md is an instructions file for Claude Code from nebrass/hve-video-director. It costs 11,214 tokens per session, scanned A, original, MIT.

A project instruction file for an agent skill that creates fixed-duration silent desktop or screen-region videos. It explains the repository, its HTML and animation renderer, helper scripts, and tests.

In plain words
What is it for?
Understanding the project architecture, editing skill content or scripts, and working with its native desktop or region capture workflow.
Why use it?
It tells coding agents how this unusual skill is structured and how to change or test it safely.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is nebrass/hve-video-director's own configuration. It tells Claude Code how to work on hve-video-director 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 hve-video-director configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nebrass/hve-video-director. 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/nebrass/hve-video-director/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nebrass/hve-video-director

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 hve-video-director CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nebrass/hve-video-director/claude-md/github.svg)](https://agentmods.dev/instructions/nebrass/hve-video-director/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nebrass/hve-video-director/claude-md"><img src="https://agentmods.dev/badge/instructions/nebrass/hve-video-director/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.

agentmods 80×15 button for hve-video-director CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nebrass/hve-video-director/claude-md"><img src="https://agentmods.dev/badge/instructions/nebrass/hve-video-director/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,214 This file is loaded in full into every session.
When invoked 11,214 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.11214 $0.11214
Opus 5 $0.05607 $0.05607
Sonnet 5 $0.02243 $0.02243
Haiku 4.5 $0.01121 $0.01121

Measured 6d ago against content hash e08aae4d6e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hve-video-director CLAUDE.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 6d 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.

curl -sL https://cdn.jsdelivr.net/npm/gsap@$V/dist/gsap.min.js | openssl dgst -sha384 -binary | base64
CLAUDE.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 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) — and GitHub Copilot CLI, which also reads CLAUDE.md — when working with code in this repository.

What this repo is

This repo is an agent skill (hve-video-director) that runs on both Claude Code and GitHub Copilot CLI, not a typical application. The "source" is prompt content (markdown) plus Python helper scripts. There is no build system or lint config; pure-stdlib helper tests live under test/. The skill is consumed by future agent sessions that invoke /hve-video-director <project-dir> (a slash command on Claude Code; invoked by name/intent on Copilot CLI). The SKILL.md frontmatter uses the Claude Code skill schema; Copilot CLI loads the skill from name/description and harmlessly ignores the Claude-only fields.

The renderer is HyperFrames (HTML + GSAP, rendered via headless Chromium). React/Remotion are no longer used.

Two things to keep distinct:

  • This repo — the skill definition (SKILL.md, reasoning/, grammar/, workflows/, templates/, patterns/, sub-agents/, scripts/, design-systems/, compat/). Edits here change behavior for all users.
  • Generated video projects — created by the skill at runtime in {project-dir}/. They contain project-plan.md, .hve/brief-state.json, context.md, storyboard.md (the official HyperFrames storyboard shape since M4 — see below), DESIGN.md, public/screenshots/, scenes/*.html, index.html (root HyperFrames composition), voiceover.mp3, out/final.mp4, and — only while a Studio review round is open — .hyperframes/frame-comments.json. None of them lives in this repo.

example/ is the committed reference build — the source artifacts of one real end-to-end run against the HyperFrames-first pipeline (a 60s promo the skill made about itself), with every per-phase approval given by a human. Media is gitignored; the MP4 ships as a Release asset.

Treat it as a record, not a fixture. Never hand-edit a file in it to make a point, and never regenerate it from a partial run: it is only worth anything while every byte is what the pipeline actually emitted. A replacement is a human-in-the-loop run — real TTS, music licensing, a headless-Chromium render, and this skill's own per-phase approvals, which no agent may self-grant (ADR-001). Do not fabricate one, and do not add a directory that only looks like the output of a real run. example/.hve/brief-state.json is the consent record that makes the claim checkable: validate_brief.py --project-dir example status must report complete, confirmed and unstale.

Read the full file on GitHub · 414 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. 6d ago Changed · +13 lines · +525 tokens per session e08aae4d6e99
  2. 10d ago First seen · 401 lines · 10,689 tokens per session scan A 032eb194bdca

Subscribe to this mod's changes

hve-video-director CLAUDE.md is an instructions file published in the GitHub repository nebrass/hve-video-director (108 stars, last pushed 9d ago), licensed MIT. It adds 11,214 tokens to every session, about $0.0561 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 2026-08-30.

Related

Other instructions, from other repositories

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

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

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

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