hve-video-director: Instructions file for GitHub Copilot

.github/copilot-instructions.md

hve-video-director copilot-instructions.md is an instructions file for GitHub Copilot from nebrass/hve-video-director. It costs 4,312 tokens per session, scanned B, original, MIT.

Project instructions for a video-director agent skill that creates fixed-length silent screen or region recordings using HyperFrames, an HTML-and-GSAP renderer.

In plain words
What is it for?
They help maintain the skill, its scripts, tests, runtime compatibility, and the workflow for generating rendered video scenes.
Why use it?
They explain that the repository contains prompts and small helper scripts rather than a conventional application, reducing the risk of editing the wrong part.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions Claude Code.

This is nebrass/hve-video-director's own configuration. It tells GitHub Copilot 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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/generate_voiceover.py --assemble-only.

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/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/nebrass/hve-video-director

Made for: GitHub Copilot.

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 copilot-instructions.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nebrass/hve-video-director/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/nebrass/hve-video-director/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,312 This file is loaded in full into every session.
When invoked 4,312 The same file — it is already loaded in full.
Security scan B 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 $0.04312 $0.04312
Opus 5.5 $0.01725 $0.01725
Sonnet 5.5 $0.00862 $0.00862
Haiku 4.5 $0.00431 $0.00431

Measured 1mo ago against content hash 25605d24e39e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

hve-video-director copilot-instructions.md scanned grade B 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 1mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

It never runs system/sudo commands or sets environment variables. Phase -1 consumes its JSON
.github/copilot-instructions.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — hve-video-director

What this repo is

This repo is an agent skill (hve-video-director) that runs on both GitHub Copilot CLI and Claude Code, 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 <video request> or use intent. Copilot CLI reads the skill's name/description and honors allowed-tools; invocation behavior must not depend on Claude-specific frontmatter. See Runtime Compatibility in SKILL.md for the question schema, companion loading, and skill-home mapping.

The renderer is HyperFrames (HTML + GSAP, rendered via headless Chromium). React/Remotion are not used.

Request scope matters. The prompt defines subject, scenario, depth, and expected result. Phase 0 focuses on that feature/product; Phase 1 preserves the requested coverage rather than forcing a generic tour. Store original request/source provenance as single-line JSON strings outside the Creative Brief in project-plan.md; do not create an intake context.md. An approved scenario inventory in the completed context owns requirement IDs; the storyboard's single Scenario Coverage prose table records their frames and actual capture/assembled evidence. No new brief/director keys or larger packets: each frame carries its own required content, and coverage IDs are not rendered. Unresolved approved requirements are not completion.

Source comes from invocation cwd or --source-dir; output is separately confirmed (--output-dir). Resolve source-local skills to absolute paths before output work. Legacy and artifact-only resumes keep their existing prerequisites; missing new metadata alone never forces discovery.

Keep two scopes distinct when editing:

  • This repo — the skill definition (SKILL.md, workflows/, templates/, patterns/, scripts/, design-systems/). 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, DESIGN.md, public/screenshots/, scenes/*.html, index.html (root HyperFrames composition), voiceover.mp3, out/final.mp4. These do not live in this repo, and no reference build is committed while its replacement is being regenerated (see above).

Read the full file on GitHub · 171 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. 1mo ago Changed · +18 lines · +541 tokens per session 25605d24e39e
  2. 2mo ago Changed · +5 lines · +116 tokens per session 9e178365e057
  3. 2mo ago First seen · 148 lines · 3,655 tokens per session scan B e931351c73ed

Subscribe to this mod's changes

hve-video-director copilot-instructions.md is an instructions file published in the GitHub repository nebrass/hve-video-director (104 stars, last pushed 1mo ago), licensed MIT. It adds 4,312 tokens to every session, about $0.0172 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

hve-video-director copilot-instructions.md compared with instructions from other repositories

hve-video-director copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hve-video-director copilot-instructions.mdnebrass/hve-video-directorInstructions file1041mo agoMITB4,312GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode