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.
npx agentmods add instructions/dubh3124/director/agents-mdgit clone --depth 1 https://github.com/dubh3124/DirectorWrote 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/dubh3124/director/agents-md)<a href="https://agentmods.dev/instructions/dubh3124/director/agents-md"><img src="https://agentmods.dev/badge/instructions/dubh3124/director/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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Contribution Guide
This file is for future agents working in this repository.
Purpose
Director is a local-first, AI-first system for creating live-application presentations. The package and repository slug are ai-recorder; the CLI command is director. Director exposes a TypeScript SDK, a local MCP server, and an A2A-shaped adapter. The SDK is the source of truth; adapters should call SDK operations instead of duplicating behavior.
Use movie/director nomenclature consistently:
Director: the production system and operator.Storyboard: the versioned production plan.Scene: a grouped chapter of related shots.Shot: one captured app moment.Stage Direction: a browser action such asgoto,click,fill,press,waitForText, orcapture.Camera Rig: capture backend, usually Playwright.Dailies: raw screenshots, recordings, diagnostics, and timing data.Final Cut: rendered MP4.Pitch Deck: editable PPTX.
Commands
Run these before handing work back:
npm run typecheck
npm test
npm run build
Run these for release or packaging work:
npm audit --audit-level=moderate
npm run pack:dry
Use the development CLI from the repo root:
npm run director -- check examples/basic/storyboard.yaml
Approval Gates
shoot and premiere operate a browser and write production artifacts, so they require approval. Do not bypass approval in agent workflows unless the user explicitly configures trusted local automation with DIRECTOR_APPROVED=1 or passes --approved.
Agents may scout, draft, and check storyboards without approval.
No-Secret Rules
Never commit:
- Real API keys, client secrets, passwords, bearer tokens, or session material.
- Private URLs, tailnet domains, tenant/customer names, or production credentials.
.envfiles, raw transcripts, screenshots, videos, generated decks, or local demo bridge scripts.- Anything under
.director/.
Use placeholder env var names in docs and examples. Keep generated/private demos in .director/local-demos/ or another ignored dot directory.
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.
- 3d ago First seen · 83 lines · 651 tokens per session scan A 98ad1d0105eb
Director AGENTS.md is an instructions file published in the GitHub repository dubh3124/Director (5 stars, last pushed 2mo ago), licensed MIT. It adds 651 tokens to every session, about $0.0033 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.
Other instructions, from other repositories
playwriter AGENTS.md
Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.
nuwax AGENTS.md
AGENTS.md instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
Cotal AGENTS.md
AGENTS.md instructions for Cotal-AI/Cotal, covering agents.md, what this is, read these first, commands and repository map.
playwright-rust CLAUDE.md
Instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.
react-redux-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/react-redux-boilerplate, covering agents.md, project overview, setup commands, testing and linting, formatting, and type checking.
adk CLAUDE.md
Instructions for inference-gateway/adk, covering claude.md, what this repo is, commands, architecture and server (server/).