agent-skills AGENTS.md

agent-skills AGENTS.md is an instructions file for Codex, OpenCode from novoads/agent-skills. It costs 4,245 tokens per session, scanned C, original, MIT.

A project guide for agent skills that use the Novoads API to create AI-generated video and image assets. It also documents setup requirements and the project’s key files.

In plain words
What is it for?
Setting up the project, checking the Novoads API key, and working with its video and image generation skills and scripts.
Why use it?
It tells an agent how the project is organised, what setup is needed, and how to handle missing API access.

Instructions file for CodexOpenCode

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 instructions/novoads/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/novoads/agent-skills

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 agent-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/novoads/agent-skills/agents-md.svg)](https://agentmods.dev/instructions/novoads/agent-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/novoads/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/novoads/agent-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,245 This file is loaded in full into every session.
When invoked 4,245 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.04245 $0.04245
Opus 5 $0.02122 $0.02122
Sonnet 5 $0.00849 $0.00849
Haiku 4.5 $0.00424 $0.00424

Measured 3d ago against content hash 2fb89a679bee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agent-skills AGENTS.md scanned grade C with 1 finding 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Every credit number shown to a user must come from a live `POST /v1/estimates` call made in the current session, and the user approves it before anything is generated. There are no rate tables in this repo — not in `MAST
AGENTS.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions

This repository is set up for AI coding agents (Cursor, Claude Code, Copilot-style tools, etc.) to generate AI video and image assets via the API documented in this repo.

First-time setup

If .env or MASTER_CONTEXT.md do not exist, tell the user to run ./scripts/setup.sh.

When the session IS the setup ("help me set this up"), setup is the whole job and the final report is SHORT — the few sentences a non-developer wants, not an engineering log. ./scripts/setup.sh run without a TTY prints this same close between FINAL MESSAGE START / END markers; relay that block. The script and the template below are mirrors — change them together. One or two status lines, then:

Setup's done — your key works. (or, when the key is missing:) One step left, the only one I can't do: create an API key at https://novoads.ai/dashboard/settings?tab=api, paste it into .env, and tell me — I'll verify it. (No account yet? The $1 trial.) (On macOS and on Linux with a desktop session, setup opens .env itself and the line becomes "I've opened .env for you — paste the key on the NOVOADS_API_KEY line, save, and tell me." It is skipped over SSH, in CI, and under NOVOADS_SETUP_NO_OPEN=1.)

What you can ask for now:

  • "Make a UGC video ad for my product" — a presenter speaks your script
  • "Make static image ads from this photo" — the 40-template library, run in batches
  • "Clone my competitors' ads" — finds their live ads, ranks them, and clones the best one for your product. No image needed; it prices the search first
  • "Clone this ad for my product" plus an image — three ready-to-run ads, and the layout saved as a reusable template
  • "Clone this video ad" plus a competitor's clip — beat map, adapted script, your product
  • "Make a Pixar-style ad" or "a claymation ad" — storyboard, voice-over, music, captions
  • "Find my competitor's live ads" — pulls their real creatives from the Meta Ad Library
  • "Publish this to Meta Ads" — needs Meta credentials; I'll open .env and walk you through
  • Also: YouTube thumbnails, burned-in captions, b-roll cutaways, a music bed

Drop product photos into references/products/ and describe the ad you want. Every generation is priced by a live estimate and shown to you before anything is spent.

Read the full file on GitHub · 191 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 First seen · 191 lines · 4,245 tokens per session scan C 2fb89a679bee

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository novoads/agent-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 4,245 tokens to every session, about $0.0212 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.