A guide for using 2DAI, a cloud service that generates images and videos, through its agent tools. It covers presets, account credit, references, character consistency, and assembling short films.

It supports image generation, image-to-video work, style transfer, reference-based creation, character consistency, and short video assembly.

It helps avoid rejected requests, unexpected spending, and inconsistent results by checking account limits and choosing an appropriate preset first.

2dai — Skill for Claude Code and Codex by 2DAICommunity

Install

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.

Any agent

npx skills add 2DAICommunity/2dai-mcp-server --skill 2dai

Clone the repo

git clone --depth 1 https://github.com/2DAICommunity/2dai-mcp-server

Made for: Claude Code, Codex.

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/skills/2daicommunity/2dai-mcp-server/2dai/github.svg)](https://agentmods.dev/skills/2daicommunity/2dai-mcp-server/2dai)

Your own site

<a href="https://agentmods.dev/skills/2daicommunity/2dai-mcp-server/2dai"><img src="https://agentmods.dev/badge/skills/2daicommunity/2dai-mcp-server/2dai/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/skills/2daicommunity/2dai-mcp-server/2dai"><img src="https://agentmods.dev/badge/skills/2daicommunity/2dai-mcp-server/2dai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,411 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00057	$0.03411
Opus 5.5	$0.00023	$0.01364
Sonnet 5.5	$0.00011	$0.00682
Haiku 4.5	$0.00006	$0.00341

Measured 5d ago against content hash 1c23b85dbf67, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

2dai 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 5d 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.

skills/2dai/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

2DAI for agents

2DAI is a generation platform (images, image-to-video, references, style transfer) with a cloud drive. You reach it through the 2dai-mcp-server tools (25 tools) with an API key. Every generation spends the account's USD credit; every result lands in the account's cloud drive as a creation with a 32-char id.

1. Session start (always)

get_account — credit, tier, key scopes and spend cap (and the key's own ceilings, when it has a policy), the presets this account may submit, the video lengths with their tier locks, the best pick open to the account (recommendation) and the engine behind each channel with what it takes (platform.engines). Never probe presets or lengths by submitting: a locked one is refused at submit (403) and wastes a round-trip.
Budget: write down credit and the key cap. Costs are charged at submit and refunded on failure.
list_creations if the account already holds references (brand masters, character sheets).

2. Quality ladder — one set of ids for every tool

Preset	Image	Video	Use it for
`fast`	quickest render	0.2 MP, quickest render with sound	drafts, layout and scenario tests
`normal`	standard resolution	0.4 MP	social drafts, moodboards
`high`	higher resolution than Normal	recommended for video — 0.4 MP at 20 steps, cleaner motion and sound	everyday clips
`max`	recommended for images — best detail / price balance	0.7 MP, sharper frames, longer render	everyday images
`ultra`	more steps and a model upscale, for prints	0.7 MP at 20 steps, slower	prints, large crops
`ultimate`	highest resolution, for final masters	1 MP at 20 steps, longest wait	final masters only

Presets open by tier (get_account resolves them — read them there; this is the reference at the time of writing):

Tier	Image	Video	Video lengths
Guest	`fast`, `normal`	—	—
Explorer	+ `high`	`fast`	1, 5 s
Holder	+ `max`	+ `normal`	+ 8 s
Believer	+ `ultra`	+ `high`	+ 10 s
Supporter	+ `ultimate`	`fast`, `normal`, `high`	+ 12 s
Founder	every preset	+ `max`, `ultra`, `ultimate`	+ 15, 17, 20 s

Read the full file on GitHub · 164 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.

5d ago Changed · +21 lines 1c23b85dbf67
7d ago Changed · +7 lines c657e6bff8dc
9d ago Changed e328c5322717
17d ago Changed ff10f2c2fd94
24d ago Changed 0d8bebd36186
27d ago Changed · +14 lines 4fe288faed96
1mo ago Changed · +10 lines f8aa8ac7ad69
1mo ago Changed 943478372bd4
1mo ago Changed 83a7662a7b01
1mo ago First seen · 112 lines · 57 tokens per session scan A e48045bf7abf

Subscribe to this mod's changes

2dai is a skill published in the GitHub repository 2DAICommunity/2dai-mcp-server (0 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 3,411 once invoked, about $0.0002 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 2026-09-10.

Creative and media

2dai next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
2dai2DAICommunity/2dai-mcp-server	Skill	0	5d ago	MIT	A	57	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code