What is local-ai-movie-workspace AGENTS.md?

A repository guide that tells coding agents how to work safely in a shared AI workspace. It covers the project’s purpose, required reading, security boundaries, and handoff rules.

Use it when working on this repository to understand its architecture, check which files to read, preserve existing changes, and avoid exposing private credentials or user data.

It gives contributors the project context and rules they need before changing code, especially around reservations, authorization, models, media, and secrets.

How linkprint/local-ai-movie-workspace configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to linkprint/local-ai-movie-workspace. 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/linkprint/local-ai-movie-workspace/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/linkprint/local-ai-movie-workspace

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/linkprint/local-ai-movie-workspace/agents-md/github.svg)](https://agentmods.dev/instructions/linkprint/local-ai-movie-workspace/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/linkprint/local-ai-movie-workspace/agents-md"><img src="https://agentmods.dev/badge/instructions/linkprint/local-ai-movie-workspace/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/linkprint/local-ai-movie-workspace/agents-md"><img src="https://agentmods.dev/badge/instructions/linkprint/local-ai-movie-workspace/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 674 This file is loaded in full into every session.

When invoked 674 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	$0.00674	$0.00674
Opus 5	$0.00337	$0.00337
Sonnet 5	$0.00135	$0.00135
Haiku 4.5	$0.00067	$0.00067

Measured 10d ago against content hash bfb71f3e0d3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

local-ai-movie-workspace 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 10d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Movie AI Workspace contributor guide

Mission

This repository turns one or more privately operated AI servers into a reservation-based creative workspace for a team. The Portal owns identity, reservations, projects, workspaces, and media. Codex or Claude Code runs inside the selected project through a persistent tmux session. Language and media models remain behind the reservation-bound Broker.

Read before changing code

Read README.md and docs/AI_INSTALL_AND_OPERATIONS_GUIDE.md.
Run git status --short and preserve every existing user change.
Read the closest nested AGENTS.md; images/workspace/AGENTS.md is the runtime policy embedded into each Workspace image.
Trace Portal -> Manager -> Broker -> adapter/Unix socket before changing an authorization, reservation, model, or media path.

Security boundaries

Never read, print, copy, commit, or share .env, Docker secret files, private keys, model-provider tokens, cookies, device codes, auth.json, user media, production database records, or runtime volumes. Database migrations and the deterministic sanitized system-configuration seeder are the only database material permitted in Git.
Keep examples on movie.example.com and the sample physical LAN 192.168.88.x. The 172.30.x ranges are isolated Docker bridge networks, not physical server addresses.
Workspaces never receive Docker, SSH, systemd, host shell, arbitrary ComfyUI workflow, or direct model-server access.
Personal and company Codex identities use separate persistent volumes. Never implement collaboration by copying an identity file between users.
Treat model names ending in uncensored as operator-supplied deployment aliases. The repository ships routing and policy, not model weights.

Skills and agent handoff

Administrator skills are built from images/workspace/admin-skills/ into /etc/codex/skills, Codex's admin skill scope.
Workspace startup must fail closed if movie-ai skills verify cannot validate required SKILL.md metadata and read-only permissions.
Use explicit $skill-name invocation for safety-critical media workflows. /skills is the human acceptance check after entering a Workspace.
Durable repository knowledge belongs here or in the runtime AGENTS.md; detailed runbooks belong in docs/AI_INSTALL_AND_OPERATIONS_GUIDE.md.

Read the full file on GitHub · 64 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.

10d ago First seen · 64 lines · 674 tokens per session scan A bfb71f3e0d3c

Subscribe to this mod's changes

local-ai-movie-workspace AGENTS.md is an instructions file published in the GitHub repository linkprint/local-ai-movie-workspace (1 stars, last pushed 13d ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 per session on Opus 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.

AI Platform Claude Code ai-filmmaking ai-infrastructure ai-server-reservation ai-workspace

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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

local-ai-movie-workspace: Instructions file for Codex