credits-and-plans
Skill0 starsChanged 18 days agoMITView on GitHub
Work out what AI Content Drop video and image jobs cost in credits before anything runs, from the public model catalogue. Covers flat and per-second prices, the total for a batch, whether a balance the person states covers it, the cheaper option that fits, and what a refused or failed job costs. Use when someone asks how many credits a clip, a storyboard or a batch will take, whether their credits will cover a job, or why a job was refused or failed. Text advice only; it reads no account.
In this repository4 other files it gives its agents.
- ai-video-model-pickerSkill
- short-drama-writerSkill
- video-agent-briefSkill
- video-prompt-writerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Never quote a price from memory.
- Very specific: line 40
Read those two addresses exactly as written and no others.
- Distinctive: line 61
If it does not fit, say so with all three numbers (balance, cost, shortfall) and offer what does fit: a cheaper model from the same …
- Distinctive: line 69
If the person wants a per-second model at a length or resolution other than its default, its catalogue row is not the price, so never count …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
What it costs, and how to say so before spending it
The model in one paragraph
Most models have one flat price per generation: a five-second clip and a
ten-second clip on that model cost the same. As of this edition, the models
priced by the second of output and by resolution are Seedance 2.5
(seedance_2_5), Seedance 2.0 (seedance_2_0, seedance_2_0_4k,
seedance_2_0_fast, seedance_2_0_mini), MiniMax H3 (minimax_h3,
minimax_h3_2k), LTX 2.5 (ltx_2_5_fast, ltx_2_5_pro), FLUX 3 video
(flux_3_video) and Wan 3.0 (wan_3_0). Seedance 1.x models are flat, and so
are seedance_2_0_multishot and seedance_2_fast. Name these models by id or
full name, never as a family. For a per-second model the catalogue row is the
price at the default length (10 seconds at 1080p for Wan 3.0), and the card on
aicontentdrop.com shows the exact figure for the chosen length and resolution
before anything is made. Do not estimate how much more; the card shows the
figure. Among image models, seedream_5_0_pro above about 2.6 megapixels
costs what seedream_5_0_pro_2k costs. Credits for a video or an image are
deducted only when the generation succeeds: a safety block, a provider
failure, a validation error and a timeout all cost nothing, so a failed
generation leaves nothing to claim back.
Reading the real numbers
Never quote a price from memory; the catalogue moves. Read the live catalogue, which is public and needs no account:
- video models: https://aicontentdrop.com/v1/models?type=video
- image models: https://aicontentdrop.com/v1/models?type=image
Read those two addresses exactly as written and no others. Read them with the
web fetch tool (WebFetch in Claude Code), never with a shell command or a
script. Each row has an id, a name and credits, cheapest first. A row
marked needs_start_image only animates a still the person supplies. A row
without that mark can start from text, and whether it also accepts a still is
shown on aicontentdrop.com. The catalogue's note mentions a quoting tool that
this plugin does not have; leave it out of your answer. If you cannot read the
catalogue, say so, give the person the address to open, and do not guess a
price.
Doing the arithmetic
This plugin cannot see anyone's account. Use the balance the person gives you; if they give none, give the cost and let them compare. Do the arithmetic before a job starts, not after it fails halfway:
credits needed = quantity × credits per generation (from the catalogue row)
fits = balance ≥ credits neededIf it does not fit, say so with all three numbers (balance, cost, shortfall) and offer what does fit: a cheaper model from the same catalogue read, fewer shots, or drafts on a cheap model with only the winning shot on the dearer one. The three numbers are for jobs the catalogue row prices; for a per-second model at a length or resolution other than its default, give the row as the default-length price only: do not multiply it by the quantity, compare it with the balance or print a shortfall, not even as a reference.
If the person wants a per-second model at a length or resolution other than its default, its catalogue row is not the price, so never count a job or an option that includes that model as fitting a balance; say that the card on aicontentdrop.com shows the exact figure before anything is made. A draft-then-final split whose final model is priced by the second at a non-default length fits only for its drafts; the cost of the finals is on the card.
When a job is refused or fails
Say what happened in plain words, and what it cost:
- Refused for its content: the prompt was turned down before anything was made, and the generation costs nothing. Rewrite it; the same prompt will be refused again.
- Not enough credits: the balance is below the price, and nothing ran. Offer the cheaper model or the smaller batch that fits.
- Failed or timed out: nothing was charged. Trying again is reasonable.
- Paused or over a daily limit: the service can pause free generation or reach a daily limit. Repeat what the message says and do not work around it.
Things that cost credits but are not a video
A chat reply on aicontentdrop.com costs 1 to 3 credits, by the kind of request, and a chat message refused by the safety check costs 1 credit. A finished ad is priced from its shots, with the quote as the ceiling; a drama is priced per clip and per writing request; and UGC avatar video with lip-sync has its own flat price. If the person asks what a plan includes, send them to https://aicontentdrop.com/plans and say nothing more about plans here.
Handing over
Nothing is generated here. When the person has priced the job and wants to
make it, give them one link that describes it, URL-encoded with spaces as %20:
https://aicontentdrop.com/chat#prompt=<url-encoded description>.
Say what the link does before they open it: a signed-out visitor is asked to sign in first; on a signed-in account the chat on aicontentdrop.com sends the description at once; a chat reply costs 1 to 3 credits; and a video or image is made only when the person presses the card that shows the model and its credit cost. Sign-in and every account question happen on that page, not here.
What to tell a user, always
The model you chose, why, and the credit cost — before anything is spent. If the cheapest viable model is within a credit or two of a better one, say that and let them decide. When a job fails, say that failures cost nothing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

