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.
curl -O https://raw.githubusercontent.com/jordanurbs/venice-video-harness/main/.agents/skills/venice-agent-guide/SKILL.mdgit clone --depth 1 https://github.com/jordanurbs/venice-video-harnessWrote 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.
[](https://agentmods.dev/skills/jordanurbs/venice-video-harness/venice-agent-guide)<a href="https://agentmods.dev/skills/jordanurbs/venice-video-harness/venice-agent-guide"><img src="https://agentmods.dev/badge/skills/jordanurbs/venice-video-harness/venice-agent-guide/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.
<a href="https://agentmods.dev/skills/jordanurbs/venice-video-harness/venice-agent-guide"><img src="https://agentmods.dev/badge/skills/jordanurbs/venice-video-harness/venice-agent-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03070 |
| Opus 5.5 | $0.00000 | $0.01228 |
| Sonnet 5.5 | $0.00000 | $0.00614 |
| Haiku 4.5 | $0.00000 | $0.00307 |
Grade A, and why
venice-agent-guide 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Venice Video Harness — Agent Operating Guide
Description
The core rules for driving the venice-video CLI from a coding agent (Hermes,
OpenClaw, Cursor, Claude Code, and others). This is the ~80/20 subset of
AGENTS.md — the rules whose absence loses money or produces unusable output.
It mirrors venice-video agent-guide (the same text ships inside the binary) and
the full rules live in AGENTS.md. Read this before running any workflow.
Keep this in sync with packages/core/src/agent/guide.ts; if a rule changes in one, change it
in the other.
Find the next step, do not guess
venice-video pipeline --jsonlists the ordered stages, their gates, and the command that advances each.venice-video status -p <project> --jsonreports where a project stands and the exact next command.- Always pass
-p <project>(and-e <episode>) explicitly. Do not rely on a selection a human may have set — a daemon- or GUI-launched agent has an arbitrary working directory, so also setHARNESS_WORKSPACEto a fixed directory.
Money is spent at queue time
- Venice bills when a render is queued, not when it downloads. A lost queue id is money already spent.
- Every queued render is recorded to
pending-jobs.jsonbefore the first poll. If a command is interrupted, re-run the same command with the same output path — that re-attaches to the paid job instead of paying again. - A killed render (for example a command timeout) is usually still running and billed. Do not treat a timeout as a failed render and retry it. Re-attach.
- Inspect in-flight work with
venice-video queue --json. Onlyqueue cleara record you know is dead.
Long renders need background invocation
generate-videos,assemble-episode,produce-episode,finish, andupscalerun 3–10 minutes.- Runners cap foreground commands (Hermes defaults to 180s, hard-caps at 600s). Run these in the background with a completion notification, not in the foreground.
- A foreground timeout kills the process but not the Venice job — see the billing rule above.
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.
- 3d ago Changed · +11 lines 1d5a086b9b89
- 4d ago Changed · +1 lines 0b861c8c1428
- 23d ago Changed eef44c4b63e2
- 1mo ago Changed · +1 lines 126522c31fab
- 1mo ago Changed · +8 lines c95682eed9ac
- 2mo ago First seen · 46 lines · 0 tokens per session scan A 367e2097f2a3
venice-agent-guide is a skill published in the GitHub repository jordanurbs/venice-video-harness (33 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,070 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…