video

A guided workflow for turning a YouTube video idea into a complete production package, including its angle, script, demo, and scene directions.

In plain words
What is it for?
Use it to develop a video concept, write its script, plan a demo, prepare runnable code and prompts, and create a scene-by-scene shooting checklist.
Why use it?
It organizes the creative and production work into three rounds, so the idea, viewer retention, script, and filming details are reviewed in sequence.

Command

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.

agentmods
npx agentmods add commands/robconery/champion/video
Clone the repo
git clone --depth 1 https://github.com/robconery/champion
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,966 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00090 $0.01966
Opus 5 $0.00045 $0.00983
Sonnet 5 $0.00018 $0.00393
Haiku 4.5 $0.00009 $0.00197

Measured 2d ago against content hash da32a8e10bb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

video 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 2d 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.

champion/commands/video.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin note: this command ships in the champion plugin, so every council agent it names is a plugin agent. When spawning any agent mentioned below, use the champion: prefix for the agent type (e.g. champion:historian, champion:north-star, champion:viewer).

Setup gate: before doing anything else, check that ~/.champion/dossier/PROFILE.md exists. If it does not, stop immediately and tell the user, politely, that the council cannot work without knowing who it fights for: run /champion:setup first (a 20–30 minute interview). Do not proceed in any form until setup is complete.

video

The video:

$ARGUMENTS

Create mode. A three-round gauntlet wrapped around a production pipeline. Round 1 decides the video is worth making and finds the sharpest angle. Round 2 architects the retention structure and writes the script. Round 3 turns the approved script into a real shoot package, scene-by-scene direction, a scouted-and-prototyped demo, runnable code and exact prompts, and a checklist the user walks through. The spine is the user's voice, the retention model, and the flywheel.

The bar: when this finishes, the user should be able to read the sheet top to bottom, tick boxes, tweak what they want, and film. Not "interesting." Usable.

Read first

  • ~/.champion/dossier/VOICE.md, the voice. Non-negotiable; everything written passes through it. If the samples are thin, say so and ask for more rather than guessing.
  • ${CLAUDE_PLUGIN_ROOT}/references/video-direction.md: the production spec: the structure model (MKBHD-clean + retention spine), the scene-sheet format, the demo scout-and-prototype protocol, the checklist. This governs shape and retention.
  • ${CLAUDE_PLUGIN_ROOT}/references/voice-scrub.md: the deslop checklist (used in Round 2).
  • ${CLAUDE_PLUGIN_ROOT}/references/marketing-playbook.md: the build is the marketing: each video teaches a real outcome and the lead magnet is the exact thing demoed.
  • Content conventions: each video is a self-contained folder ~/.champion/work/videos/NN-slug/ (episode number = production order, never changes; create the folders on demand) holding script.md (the scene sheet + the voiceover script), a folder README.md, and a shorts/ subfolder. Frontmatter on script.md: episode, title, status, format, length, publish_date, version. Add a row to the index at ~/.champion/work/videos/README.md. The user's shared lead magnet, if one exists, lives at ~/.champion/work/lead-magnet/ and is NOT copied into episode folders, videos reference it.

Read the full file on GitHub · 68 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. 2d ago First seen · 68 lines · 90 tokens per session scan A da32a8e10bb5

Subscribe to this mod's changes

video is a command published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 90 tokens to every session and 1,966 once invoked, about $0.0005 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.