venice-video-harness: Command for Claude Code

.agents/commands/lock-characters.md

lock-characters is a command for Claude Code from jordanurbs/venice-video-harness. It costs 0 tokens per session (322 once invoked), scanned A, original, MIT.

A command that creates reference images for the characters in a storyboard project. These references show each character from the front, at an angle, in profile, and full body.

In plain words
What is it for?
Use it to lock all characters or one selected character before generating storyboard images.
Why use it?
It provides visual targets for keeping a character’s face, body, clothing, and appearance consistent across generated scenes.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: installed under .agents/ (shared by several agents).

This is jordanurbs/venice-video-harness's own configuration. It tells Claude Code how to work on venice-video-harness 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 venice-video-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jordanurbs/venice-video-harness. 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/jordanurbs/venice-video-harness/main/.agents/commands/lock-characters.md
Clone the repo
git clone --depth 1 https://github.com/jordanurbs/venice-video-harness

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 lock-characters

README.md
[![agentmods](https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/lock-characters/github.svg)](https://agentmods.dev/commands/jordanurbs/venice-video-harness/lock-characters)
Your own site
<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/lock-characters"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/lock-characters/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 lock-characters

Your own site · 80×15
<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/lock-characters"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/lock-characters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 322 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 $0.00000 $0.00322
Opus 5 $0.00000 $0.00161
Sonnet 5 $0.00000 $0.00064
Haiku 4.5 $0.00000 $0.00032

Measured 10d ago against content hash b9ce762f341b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lock-characters 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 10d 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.

.agents/commands/lock-characters.md · 43 lines

What it actually says

/lock-characters

Generate reference images for characters to maintain visual consistency across the storyboard.

Usage

/lock-characters --project <project-dir> [--character <name>]

Arguments

  • --project: Project output directory (required)
  • --character: Lock a specific character only (optional, defaults to all)

What This Does

  1. Loads the project state with extracted character descriptions
  2. For each character (or specified character):
    • Generates 4 reference images: front face, 3/4 view, profile, full body
    • Uses the character's exhaustive description as the prompt
    • Tracks the generation seed for reproducibility
  3. Saves reference images as PNG files in <project>/characters/<name>/
  4. Marks characters as "locked" in project state

Character Consistency Strategy

  • Layer 1: Exhaustive text description injected into every prompt
  • Layer 2: Reference images (base64) passed to Venice Nano Banana Pro multi-ref
  • Layer 3: Edit endpoint correction if face drifts

Execution

npx tsx src/cli.ts lock-characters --project "$project_dir" --character "$name"

Output

  • Reference images saved to disk
  • Character lock status in project state
  • Next step: run /set-aesthetic

Example

/lock-characters --project output/my-film
/lock-characters --project output/my-film --character "SARAH"
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. 10d ago First seen · 43 lines · 0 tokens per session scan A b9ce762f341b

Subscribe to this mod's changes

lock-characters is a command published in the GitHub repository jordanurbs/venice-video-harness (31 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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 2026-08-30.