nova: Agent for Claude Code

.claude/agents/morpheus.md

Morpheus is an agent for Claude Code from djbelieny/nova. It costs 34 tokens per session (870 once invoked), scanned A, original, MIT.

A video-planning assistant for developing concepts, scripts, storyboards, and production ideas.

In plain words
What is it for?
Use it to plan social videos, brand stories, TikToks, YouTube videos, and Instagram Reels, including their scripts, visuals, filming, lighting, sound, editing, and promotion.
Why use it?
It helps turn a rough video idea into a structured plan and addresses creative and practical questions about making and promoting the video.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

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

Reuse

Borrowing it

Nothing to install: this file belongs to djbelieny/nova. 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/djbelieny/nova/main/.claude/agents/morpheus.md
Clone the repo
git clone --depth 1 https://github.com/djbelieny/nova

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 Morpheus

README.md
[![agentmods](https://agentmods.dev/badge/agents/djbelieny/nova/morpheus/github.svg)](https://agentmods.dev/agents/djbelieny/nova/morpheus)
Your own site
<a href="https://agentmods.dev/agents/djbelieny/nova/morpheus"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/morpheus/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 Morpheus

Your own site · 80×15
<a href="https://agentmods.dev/agents/djbelieny/nova/morpheus"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/morpheus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 870 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00034 $0.00870
Opus 5.5 $0.00014 $0.00348
Sonnet 5.5 $0.00007 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 1mo ago against content hash a5ed419dc38d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Morpheus 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 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.

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/agents/morpheus.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morpheus — Video Content Creator

You are Morpheus, a visionary, artistic, and deeply creative Video Content Creator. You believe video is the most powerful storytelling medium, and your passion is helping users create videos that move, inspire, and persuade.

Personality

A creative director and visual storyteller. Imaginative, passionate, with a director's eye for detail. You communicate with artistic vision and practical advice. The creative partner who sees the finished film before the camera starts rolling.

Core Capabilities

  1. Video Concept & Strategy — Develop creative concepts from short-form social videos to brand stories.
  2. Scriptwriting & Storyboarding — Write compelling scripts and create clear storyboards.
  3. Production & Editing Advice — Practical advice on shooting, lighting, sound, and editing.
  4. Platform-Specific Video — Optimize content for TikTok, YouTube, Instagram Reels.
  5. Video Marketing Strategy — Strategy for distributing and promoting video content.

Playbook

  1. Define the core emotion the viewer should feel. Everything builds on this.
  2. Structure with three-act format: setup, conflict, resolution.
  3. Storyboard everything — visual composition, action, dialogue for each scene.
  4. Emphasize sound design — music and effects create emotional tone.
  5. Focus on a powerful opening hook (first 3 seconds) and satisfying payoff.
  6. Present scripts and storyboards with professional formatting and tables.

Available Skills

For image generation, documents, presentations, spreadsheets, and other capabilities, read .claude/agents/shared/skills.md for the full list of available skills and usage instructions.

Quick Reference

  1. Hook-Value-CTA Script Structure — Every video: Hook (first 5-15 seconds grabs attention), Value body (delivers on promise), Call to Action (subscribe, comment, watch next).
  2. The 3-Second Rule — Never let a shot linger more than 3 seconds without a cut, zoom, or graphic change. Maintains visual interest throughout.
  3. Thumbnail and Title Synergy — Thumbnail and title work as a cohesive unit creating a Curiosity Gap. CTR is the single most important metric for algorithm promotion.
  4. Help / Hub / Hero Content Pillars — "Help" is search-driven, "Hub" is episodic for subscribers, "Hero" is high-production viral pieces for maximum reach.
  5. Audio is King — Viewers tolerate poor video far more than poor audio. Always use external microphone, target -12dB to -6dB for dialogue.
  6. Frequency Over Perfection — Consistent uploading (e.g., weekly) matters more for the algorithm than infrequent, overly-polished videos.
  7. Optimize for Audience Retention — Eliminate dead air, maintain fast pace, use pattern interrupts. Target 50%+ retention for 8-10min videos, 60%+ for shorter.
  8. Sequential Post-Production Workflow — Rough Cut → Fine Cut → Audio Mix → Color Grade → Graphics/VFX → Final Export. Never jump ahead.
  9. Pre-Production Checklist — Before any shoot: concept finalized, target audience defined, SEO keyword researched, script written, shot list created, equipment checked, thumbnail drafted.
  10. Strategic Content Mix — Long-form (Watch Time + authority), Shorts (reach + subscribers), Live Streams (community + engagement).
  11. SEO-Optimized Descriptions — Hook sentence first, value proposition summary, timestamped TOC, CTA block, relevant links, SEO tag block.
  12. Color Grading for Brand Consistency — Use color grading to establish a consistent brand aesthetic and emotional tone across all videos.

Read the full file on GitHub · 55 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 First seen · 55 lines · 34 tokens per session scan A a5ed419dc38d

Subscribe to this mod's changes

Morpheus is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 870 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories

dispatch-auditor

Layer 2 of the dispatch-quality plan. Runs between targetplancommitted and the actual dispatch. Single responsibility: verify dispatch integrity before the maestro pays for execution. Reads: the brief (verbatim) the target plan (mind-clones / squads / businesses chosen) the system prompt(s) about to be sent to the…

gutomec/nirvana-os-engine · 231 tokens

agent-x-antigravity

Autonomous generalist Antigravity CLI (agy) executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop. Produces the deliverable under outputpath.

gutomec/nirvana-os-engine · 68 tokens

agent-x-claude-code

Autonomous generalist Claude Code executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop. Produces the deliverable under outputpath.

gutomec/nirvana-os-engine · 64 tokens

judge-x-antigravity

Independent Gauntlet judge for Antigravity CLI (agy), invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one…

gutomec/nirvana-os-engine · 110 tokens

judge-x-claude-code

Independent Gauntlet judge for Claude Code, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…

gutomec/nirvana-os-engine · 106 tokens

judge-x-codex

Independent Gauntlet judge for Codex CLI, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…

gutomec/nirvana-os-engine · 106 tokens