shubi-shot-director: Instructions file for Codex

AGENTS.md

shubi-shot-director AGENTS.md is an instructions file for Codex, OpenCode from maoxiansheng0323-a11y/shubi-shot-director. It costs 764 tokens per session, scanned A, original, MIT.

Repository instructions for Shubi Shot Director, a tool that turns written shot descriptions into editable rough 3D scenes and reference images. They define what the product includes and what it must not include.

In plain words
What is it for?
Use it when designing or changing scene data, parsing shot descriptions, exporting camera references, handling project profiles, or checking that new work stays within the product boundary.
Why use it?
They keep the project focused on rough camera planning and prevent private project information or production features from being added accidentally. They also define where scene state and language decisions belong.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is maoxiansheng0323-a11y/shubi-shot-director's own configuration. It tells Codex and OpenCode how to work on shubi-shot-director itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shubi-shot-director configures →

Reuse

Borrowing it

Nothing to install: this file belongs to maoxiansheng0323-a11y/shubi-shot-director. 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/maoxiansheng0323-a11y/shubi-shot-director/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/maoxiansheng0323-a11y/shubi-shot-director

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 shubi-shot-director AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maoxiansheng0323-a11y/shubi-shot-director/agents-md/github.svg)](https://agentmods.dev/instructions/maoxiansheng0323-a11y/shubi-shot-director/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/maoxiansheng0323-a11y/shubi-shot-director/agents-md"><img src="https://agentmods.dev/badge/instructions/maoxiansheng0323-a11y/shubi-shot-director/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.

agentmods 80×15 button for shubi-shot-director AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/maoxiansheng0323-a11y/shubi-shot-director/agents-md"><img src="https://agentmods.dev/badge/instructions/maoxiansheng0323-a11y/shubi-shot-director/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 764 This file is loaded in full into every session.
When invoked 764 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00764 $0.00764
Opus 5 $0.00382 $0.00382
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 13d ago against content hash 46f5d1731117, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

shubi-shot-director 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 13d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shubi Shot Director repository rules

Mission

Build Shubi Shot Director: a Codex Skill-driven graybox camera previs tool that converts natural-language shot descriptions into editable 3D scenes and exports perspective reference images.

Product boundary

This repository ends at graybox previs export.

Do not implement final image generation, art-prompt pipelines, production asset management, visual-novel integration, animation authoring, physics gameplay, or project-specific character systems.

Open-source cleanliness

  • Never introduce private project names, proprietary character data, unpublished artwork, credentials, or machine-specific absolute paths.
  • Keep all built-in examples generic.
  • Load project-specific aliases only from an explicitly supplied external project-profile.json.
  • Never copy external profile content into this repository, saved scenes, logs, screenshots, or fixtures.

Architecture

  • SceneSpec is the only persistent scene state.
  • Host Codex is the sole semantic authority for user language, explicitly supplied external profile aliases, ambiguity decisions, IntentReport, complete SceneSpec, and incremental ScenePatch authoring.
  • Use “host semantic compile” for that reasoning step. Use “runtime structured compile” only for deterministic parsing, normalization, intent coverage, constraints, and session mutation; the runtime must never infer language meaning.
  • Initial natural-language requests may cause Host Codex to author a complete SceneSpec plus create IntentReport and submit their structured envelope.
  • Every later natural-language edit must cause Host Codex to author one minimal, schema-validated ScenePatch plus modify IntentReport against the exact current sceneId and baseRevision.
  • The runtime, bridge, and scripts must not accept prompts, raw wording, profiles, aliases, credentials, tokens, models, providers, model endpoints, or non-loopback network routes.
  • Host account or KEY mode is outside the Director contract. Never inspect or pass host credentials into Director arguments, files, processes, logs, or artifacts.
  • The local SceneSession is authoritative. React and Three.js objects are projections of its current revision.
  • Editor camera, selection, hover state, panel layout, and live drag drafts are UI state and must not be saved in SceneSpec.
  • Keep deterministic transforms, constraints, persistence, and export outside model reasoning.
  • Do not expose arbitrary JSON-path mutation. Public patches must use the domain operation allowlist.
  • Preserve saved-scene compatibility through explicit schema versions and migrations.
  • Preserve direct scene create --file and patch apply --file only for callers that already possess structured data; natural-language work uses host-authored scene submit --file and patch submit --file envelopes.

Read the full file on GitHub · 58 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. 13d ago First seen · 58 lines · 764 tokens per session scan A 46f5d1731117

Subscribe to this mod's changes

shubi-shot-director AGENTS.md is an instructions file published in the GitHub repository maoxiansheng0323-a11y/shubi-shot-director (243 stars, last pushed 1mo ago), licensed MIT. It adds 764 tokens to every session, about $0.0038 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 2026-08-30.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens