venice-video-harness: Instructions file for Codex

AGENTS.md

venice-video-harness AGENTS.md is an instructions file for Codex, OpenCode from jordanurbs/venice-video-harness. It costs 42,421 tokens per session, scanned A, original, MIT.

Project instructions for Venice Video Harness, an agent-operated system for creating consistent videos with Venice models. It covers reference-driven generation, reusable workflows, model choices, and media archiving.

In plain words
What is it for?
Planning and running video workflows with recurring characters, fixed visual styles, reference images, and the narrative example included in the project.
Why use it?
They tell a coding agent how the harness works and how to preserve generated media while using its available video, image, audio, and music capabilities.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

This is jordanurbs/venice-video-harness's own configuration. It tells Codex and OpenCode 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.md
Clone the repo
git clone --depth 1 https://github.com/jordanurbs/venice-video-harness

Made for: Codex, OpenCode.

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 venice-video-harness AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jordanurbs/venice-video-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/jordanurbs/venice-video-harness/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42,421 This file is loaded in full into every session.
When invoked 42,421 The same file — it is already loaded in full.
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 $0.42421 $0.42421
Opus 5.5 $0.16968 $0.16968
Sonnet 5.5 $0.08484 $0.08484
Haiku 4.5 $0.04242 $0.04242

Measured 3d ago against content hash 599ea27f45ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

venice-video-harness AGENTS.md 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 3d 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.md · 845 lines

How it starts

The opening of the file, as written. The whole thing — 845 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Venice Video Harness

This workspace is an agent-first, Venice-optimized harness for consistency-first video creation at any length and format.

It is meant to be operated through natural language by any coding agent (opencode, Claude Code, Cursor, Codex, etc.). The user should not be asked to run terminal commands manually. The agent reads the rules, selects the right playbooks, and executes code as needed.

The shared VENICE_API_KEY lives in .env and is sourced by many scripts: do not move or rename .env.

Contract For Downstream Apps (SSOT)

This repository is the upstream single source of truth (SSOT) for Venice video generation and editing functionality. Multiple app UIs build on top of it. All functionality and features live downstream of this repository.

Apps build UIs on top. They do not re-implement harness functionality.

The Upstream-First Rule

Every new capability, model integration, routing rule, or bug fix lands in this repository first.

If an app needs something the harness does not do, the builder agent requests the feature here (see How To Request A Feature). The agent does not build a local variant. Local variants fork behavior and drift.

How To Request A Feature

Open a GitHub issue with the Feature Request template (.github/ISSUE_TEMPLATE/feature_request.md). Include:

  • The app name.
  • The workflow the app is building.
  • The harness command or module involved.
  • The expected behavior.
  • Why it belongs upstream.

How To Report A Bug

Open a GitHub issue with the Bug Report template (.github/ISSUE_TEMPLATE/bug_report.md). Include:

  • The harness version or commit.
  • The Node version and the operating system.
  • The exact command or playbook.
  • The model IDs involved.
  • The expected behavior and the actual behavior.
  • The full error output.
  • Any provenance sidecars (*.provenance.json) or recipe sidecars (*.recipe.json) for the affected assets.

How To Send A Pull Request

Follow CONTRIBUTING.md: run the tests with no key and an empty VENICE_VIDEO_CONFIG_DIR, add a CHANGELOG.md entry under ## Unreleased, re-run npm run manifest after registry changes, and report any paid probes in the PR body. CI runs both suites on Linux and macOS and fails any test that reaches the Venice API.

Read the full file on GitHub · 845 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. 3d ago Changed · +59 lines · +6,864 tokens per session 599ea27f45ca
  2. 4d ago Changed · +8 lines · +1,001 tokens per session ab59f6881682
  3. 23d ago Changed · +7 lines · +554 tokens per session a5d2728eb91b
  4. 24d ago Changed · +63 lines · +1,790 tokens per session 1e889e26535f
  5. 1mo ago Changed · +1,422 tokens per session 65ec28bf93d7
  6. 1mo ago Changed · +864 tokens per session f8602f7bff37
  7. 1mo ago Changed · +51 lines · +4,357 tokens per session b8925090d805
  8. 2mo ago First seen · 657 lines · 25,569 tokens per session scan A 653c91bc432f

Subscribe to this mod's changes

venice-video-harness AGENTS.md is an instructions file published in the GitHub repository jordanurbs/venice-video-harness (33 stars, last pushed yesterday), licensed MIT. It adds 42,421 tokens to every session, about $0.1697 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens