run-pipeline

run-pipeline is a command for Claude Code from danielrosehill/Claude-AI-Video-Producer-Plugin. It costs 26 tokens per session (306 once invoked), scanned A, original, MIT.

A command that runs a predefined sequence of AI generation steps for one video shot. A pipeline is a saved chain of model calls and intermediate files.

In plain words
What is it for?
Use it to generate a shot from its storyboard brief, save outputs and prompts, record the production history, and place the final result in the raw clips folder.
Why use it?
It makes each stage visible and recorded, so you can inspect an intermediate result and decide whether to continue, retry, change it, or stop.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ai-video-producer plugin — 11 skills, 11 commands, 7 agents, 3 MCP servers shipped together

Good fit Use it to generate a shot from its storyboard brief, save outputs and prompts, record the production history, and place the final result in the raw clips folder.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline
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/danielrosehill/Claude-AI-Video-Producer-Plugin

Made for: Claude Code.

Or install ai-video-producer, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 7 agents, 3 MCP servers.

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 run-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline/github.svg)](https://agentmods.dev/commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline)
Your own site
<a href="https://agentmods.dev/commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline/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 run-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-ai-video-producer-plugin/run-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 306 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 $0.00026 $0.00306
Opus 5 $0.00013 $0.00153
Sonnet 5 $0.00005 $0.00061
Haiku 4.5 $0.00003 $0.00031

Measured 12d ago against content hash 9638b4dd28ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

run-pipeline 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 12d 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.

commands/run-pipeline.md · 25 lines

What it actually says

Arguments: $ARGUMENTS

Parse the pipeline name and shot number. Then:

  1. Read pipelines/<pipeline-name>.md — this defines the chain of model calls and intermediate outputs.
  2. Read scripts/storyboards/<shot-number>-*.md — the per-shot brief.
  3. Read brief/tools-and-models.md to confirm model selections.
  4. For each step in the pipeline:
    • State what you're about to do and the expected output path.
    • Execute the model call (via the appropriate MCP/CLI/API the user has set up).
    • Save the artefact to generation/<modality>/NN-shortname-vN.ext.
    • Save the prompt + model + parameters to generation/prompts/NN-shortname-vN.md.
    • Append a line to logs/production-log.md.
    • Pause and surface the intermediate output. Ask whether to proceed, retry with adjustments, or abort.
  5. After the final step, copy the result into clips/raw/ and remind the user to /promote-take if it's a keeper.

If the pipeline file doesn't exist, list available pipelines and offer to create a new one.

If the shot brief is missing, tell the user to run /storyboard first.

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. 12d ago First seen · 25 lines · 0 tokens per session scan A 9638b4dd28ad

Subscribe to this mod's changes

run-pipeline is a command published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 306 once invoked, about $0.0001 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.