Borrowing it
Nothing to install: this file belongs to onimusya/media-gen. 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/onimusya/media-gen/main/AGENTS.mdgit clone --depth 1 https://github.com/onimusya/media-genWrote 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/instructions/onimusya/media-gen/agents-md)<a href="https://agentmods.dev/instructions/onimusya/media-gen/agents-md"><img src="https://agentmods.dev/badge/instructions/onimusya/media-gen/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01505 | $0.01505 |
| Opus 5 | $0.00753 | $0.00753 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
media-gen AGENTS.md scanned grade A 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 7d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Integration Guide
This document explains how AI agents (Claude Code, Codex CLI, OpenAI Agents, custom agent apps) can discover and use media-gen-cli.
Overview
media-gen-cli is designed for programmatic use by AI agents. It provides:
- Structured JSON output for reliable parsing
- Dry-run mode for cost-safe validation
- A skill file that agents can read to learn capabilities
- Default provider/model configuration so agents don't need to hardcode choices
- Consistent error codes for programmatic handling
Discovery
Agents discover the CLI through the skill file:
skills/media-generation/skill.md
This file describes all commands, required environment variables, output format, and usage examples.
Execution
The CLI is a self-contained Node.js script:
node ./skills/media-generation/scripts/media-gen.mjs <command> [options] --json
Requirements:
- Node.js 18+
- Environment variables set in
.envat the project root
Agent Workflow
1. Check Configuration
Before generating media, validate the setup:
node ./skills/media-generation/scripts/media-gen.mjs config validate --json
This returns which providers are configured and their capabilities.
2. Dry Run
Use --dry-run to validate inputs without incurring costs:
node ./skills/media-generation/scripts/media-gen.mjs image generate \
--prompt "A landscape" --dry-run --json
3. Generate
Run without --dry-run to produce output:
node ./skills/media-generation/scripts/media-gen.mjs image generate \
--prompt "A pixel art dragon" \
--output ./outputs/dragon.png \
--json
4. Parse Response
All --json responses have an ok boolean:
// Success
{ "ok": true, "type": "image", "outputFile": "./outputs/dragon.png", ... }
// Error
{ "ok": false, "error": { "code": "...", "message": "...", "suggestion": "..." } }
Default Configuration
Set defaults in .env so agents don't need to specify provider/model each time:
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.
- 7d ago First seen · 223 lines · 1,505 tokens per session scan A 9b25a2459300
media-gen AGENTS.md is an instructions file published in the GitHub repository onimusya/media-gen (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,505 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.