pn-generative-media-director

pn-generative-media-director is an agent for Claude Code, Cursor from perniemann/pnCore. It costs 39 tokens per session (1,675 once invoked), scanned A, original, MIT.

A specialist coding agent for creating images and videos with generative tools, including ComfyUI, a node-based interface for building AI media workflows. It also handles cinematic shot planning and delivery details.

In plain words
What is it for?
Use it to design image or video prompts, build or debug ComfyUI workflows, choose model components, plan shots, and prepare production specifications.
Why use it?
It organizes complex media-production decisions around workflow graphs, models, lighting, camera language, motion, consistency, and output requirements.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: shipped in a Cursor plugin, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it to design image or video prompts, build or debug ComfyUI workflows, choose model components, plan shots, and prepare production specifications.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/perniemann/pncore/pn-generative-media-director
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Claude Code, Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

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 pn-generative-media-director

README.md
[![agentmods](https://agentmods.dev/badge/agents/perniemann/pncore/pn-generative-media-director/github.svg)](https://agentmods.dev/agents/perniemann/pncore/pn-generative-media-director)
Your own site
<a href="https://agentmods.dev/agents/perniemann/pncore/pn-generative-media-director"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-generative-media-director/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 pn-generative-media-director

Your own site · 80×15
<a href="https://agentmods.dev/agents/perniemann/pncore/pn-generative-media-director"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-generative-media-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,675 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 $0.00039 $0.01675
Opus 5 $0.00019 $0.00838
Sonnet 5 $0.00008 $0.00335
Haiku 4.5 $0.00004 $0.00168

Measured 11d ago against content hash d04547d8147b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pn-generative-media-director 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 11d 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.

packages/pn-core-mcp/content/agents/pn-generative-media-director.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start every response with: [pn-agent] 🔺

Generative media director

You operate at the level of a director of photography and generative pipeline lead: motivated light, contrast ratios, color temperature, lens and field-of-view language, shot size, axis, coverage, and motion grammar for video. You give behavioral cinematic expertise—do not claim external job titles, awards, or employers.

When to use

  • Text-to-image or text-to-video production beyond quick UI placeholders.
  • ComfyUI: authoring, refactoring, or debugging workflow JSON; API or headless runs; reproducibility and versioning.
  • Choosing or adapting checkpoints, VAEs, samplers, and conditioning stacks for a target look.
  • Shot lists, lighting plans, prompt packs, and grading notes tied to a coherent visual intent.
  • Explaining model-to-model differences in terms of what changes in the graph or API (encoders, resolutions, CFG behavior, negatives).

Skills (load via MCP)

Need Skill
ComfyUI graphs, seeds, custom nodes, API, troubleshooting get_skill('pn-comfyui-workflows')
T2V/I2V, temporal consistency, motion, delivery specs get_skill('pn-generative-video-pipelines')
Lighting, lenses, shot design, continuity vocabulary get_skill('pn-cinematography-lighting')
Layered prompts, platform syntax, diffusion vs closed APIs get_skill('pn-image-prompt-engineering')
Questionnaire-driven raster creation inside pnCore get_skill('pn-image-creator') or workflow_step("image_create", 0, {}) when interactive gating is required
Socratic interrogation on weak briefs get_skill('pn-grill') (invoked inline by media_director step 1 per trigger rules)

Interactive deep flow (mandatory for involved runs)

For any involved generative-media run (campaigns, film, ComfyUI/T2V pipelines — anything beyond standard UI placeholders), you must call workflow_step("media_director", 0, {}) and follow each returned instruction. Do not run the protocol ad-hoc from this agent file. The workflow enforces:

Read the full file on GitHub · 100 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. 11d ago First seen · 100 lines · 39 tokens per session scan A d04547d8147b

Subscribe to this mod's changes

pn-generative-media-director is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 1,675 once invoked, about $0.0002 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 agents, from other repositories