What is sanzaru AGENTS.md?

Contributor instructions for the Sanzaru Python project, an MCP server that connects coding agents to media-generation tools. MCP is a standard way for an AI agent to call tools provided by another program.

Use them to set up Sanzaru, run its server, connect it to Codex, generate or download media, check job status, manage references, and follow the project's coding conventions.

They explain how to install, run, connect to, and smoke-test the server, avoiding setup mistakes. They also document the available video, image, and reference-image operations.

How TJC-LP/sanzaru configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to TJC-LP/sanzaru. 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/TJC-LP/sanzaru/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/TJC-LP/sanzaru

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tjc-lp/sanzaru/agents-md/github.svg)](https://agentmods.dev/instructions/tjc-lp/sanzaru/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tjc-lp/sanzaru/agents-md"><img src="https://agentmods.dev/badge/instructions/tjc-lp/sanzaru/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tjc-lp/sanzaru/agents-md"><img src="https://agentmods.dev/badge/instructions/tjc-lp/sanzaru/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 889 This file is loaded in full into every session.

When invoked 889 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.

Model	Per session	Once invoked
Fable 5.1	$0.00889	$0.00889
Opus 5.5	$0.00356	$0.00356
Sonnet 5.5	$0.00178	$0.00178
Haiku 4.5	$0.00089	$0.00089

Measured today against content hash ccdcaa12669e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sanzaru 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 today.

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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

This document helps contributors work effectively in this repository.

Project Structure & Module Organization

src/sanzaru/ — MCP server (entrypoint server.py, CLI sanzaru).
videos/, images/ — Downloaded videos and reference images (git-ignored).
README.md — Setup and tool usage; setup.sh — interactive setup; .mcp.json — sample MCP config.

Build, Test, and Development Commands

Install deps: uv sync (use uv venv first if needed).
Run server: uv run sanzaru (loads .env).
Quick start: ./setup.sh (prompts for OPENAI_API_KEY, creates folders, installs deps). Add HF_KEY (Higgsfield API key, key_id:key_secret) for video.
Codex integration (from repo root):
- codex mcp add sanzaru -- uv run --directory "$(pwd)" sanzaru
Smoke test (via MCP tools): create_video(..., dry_run=true) to price a job for free, then create a video/image and wait_for([id], download=true) (see README for the tool list).

Video Toolkit & Prompting (Higgsfield; Sora was removed by OpenAI on 2026-09-24)

Tools: create_video, edit_video, extend_video, get_video_status, download_video, cancel_video, list_local_videos, inspect_video_frame; images: create_image, generate_image, edit_image, get_image_status, download_image; refs: list_reference_images, prepare_reference_image; waiting: wait_for.
Flows: Video only (create → wait_for(download=true)) or Image → Video (generate image → prepare_reference_image(aspect_ratio=...) → create_video(reference_image=...)). Every video job is priced first; pass max_cost_usd.
Prompting: see docs/video-prompting-guide.md. Think “action + subject + scene + style + camera + lighting + mood”.
Example: create_video(prompt="wide tracking shot of a neon-lit rainy alley, cinematic, 35mm", aspect_ratio="16:9", duration=8, max_cost_usd=5)

Coding Style & Naming Conventions

Python 3.11+, typed (prefer TypedDict, explicit return types).
snake_case for functions/vars, PascalCase for classes, constants UPPER_SNAKE.
Lint/format with ruff (line length 120, py311). Run: uv run ruff check . and uv run ruff format ..

Read the full file on GitHub · 45 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.

today Changed ccdcaa12669e
1mo ago Changed · +167 tokens per session 2090efde2892
2mo ago First seen · 45 lines · 722 tokens per session scan A 15657eb92b5e

Subscribe to this mod's changes

sanzaru AGENTS.md is an instructions file published in the GitHub repository TJC-LP/sanzaru (6 stars, last pushed yesterday), licensed MIT. It adds 889 tokens to every session, about $0.0036 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 2026-08-31.

sanzaru AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sanzaru AGENTS.mdTJC-LP/sanzaru	Instructions file	6	yesterday	MIT	A	889	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

sanzaru: Instructions file for Codex