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 skills add manishiitg/coding-agent-loop --skill seeddance-apigit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/skills/manishiitg/coding-agent-loop/seeddance-api)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/seeddance-api"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/seeddance-api/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.
<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/seeddance-api"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/seeddance-api.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00095 | $0.01142 |
| Opus 5.5 | $0.00038 | $0.00457 |
| Sonnet 5.5 | $0.00019 | $0.00228 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
seeddance-api 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call the direct Seeddance API safely
This skill covers the service documented at https://www.seeddance.io/docs.
It is a separate provider from fal.ai and from ByteDance's own enterprise
platform. Do not send a fal key to it, translate fal endpoint IDs into it, or
assume access and pricing are identical.
Current documentation starting points:
https://www.seeddance.io/docs/authenticationhttps://www.seeddance.io/docs/modelshttps://www.seeddance.io/docs/createVideoGenerationhttps://www.seeddance.io/docs/getTaskhttps://www.seeddance.io/docs/getCredits
Authenticate without exposing the credential
Read the deployment credential only from SECRET_SEEDANCE_API_KEY. Send it as
the bearer token required by the /v1 API. Never print, echo, log, persist,
return, or interpolate its value into a durable command transcript. Do not put
it in a project .env file. If the variable is absent, mark the direct provider
unavailable. Fall back to fal only when SECRET_FAL_KEY exists and the approved
production plan allows that provider switch.
A read-only GET https://www.seeddance.io/v1/credits is the preferred access
check before planning a paid direct run. Record only whether authentication
succeeded and the returned credit count; never record request headers. A valid
key does not guarantee that the account's plan permits every model.
Discover the model before spending
As checked on 2026-08-17, the public model catalog lists:
seedance-1.0-pro-fast
seedance-1.5-pro
seedance-2.0
seedance-2.0-fast
seedance-2.0-mini
Re-read the live catalog and create schema before every production. Store the
chosen direct model ID, allowed duration, quality, aspect ratio, media limits,
audio support, price, and plan entitlement in the capability record. Never use
a fal model ID such as bytedance/seedance-2.5/text-to-video here.
As checked on 2026-08-17, the direct public documentation says Seedance 2.5 is
not yet available there and requests for seedance-2.5 return
422 model_not_available. Do not send a direct 2.5 request just because fal
exposes a 2.5 endpoint. Recheck the direct model catalog at selection time;
provider availability, schema, and pricing are separate contracts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 105 lines · 95 tokens per session scan A 5cc78b4808e8
seeddance-api is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 95 tokens to every session and 1,142 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
voice-ai-integration-engineer
Skill "voice-ai-integration-engineer" from aimerdoux/wavex-os, covering 🎙️ voice ai integration engineer agent, 🧠 your identity & memory, 🎯 your core mission, end-to-end transcription pipeline engineering and structured output and downstream integration.
data-engineer
Skill "data-engineer" from aimerdoux/wavex-os, covering data engineer agent, 🧠 your identity & memory, 🎯 your core mission, data pipeline engineering and data platform architecture.
agency-ai-engineer
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
model-serving-and-monitoring
Use when a model is served online (FastAPI, BentoML) or scored in batch, when changing how a model artifact is loaded or versioned, or when adding drift, quality or prediction monitoring and a rollout plan for a new model.
fiber-rest-api
Use when adding or changing a Go HTTP endpoint — Fiber v2 or v3 (detect which), thin handlers, central error mapping, boundary validation; the same rules apply to net/http, chi, echo or gin.