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 oyi77/1ai-skills --skill replicate-runnergit clone --depth 1 https://github.com/oyi77/1ai-skillsWrote 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/oyi77/1ai-skills/replicate-runner)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/replicate-runner"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/replicate-runner.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 5.1 | $0.00040 | $0.03537 |
| Opus 5 | $0.00020 | $0.01768 |
| Sonnet 5 | $0.00008 | $0.00707 |
| Haiku 4.5 | $0.00004 | $0.00354 |
Grade A, and why
replicate-runner scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
img_bytes = requests.get(base_url).content How it starts
The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replicate Runner
When to Use
Trigger phrases:
-
"replicate runner"
-
"Run AI models on Replicate cloud API"
-
When running AI models without managing GPU infrastructure
-
When generating images, videos, or audio with state-of-the-art models
-
When deploying custom models to a cloud API
-
When chaining multiple AI models in a pipeline
Anti-Rationalization Table
| Excuse | Reality | Rule |
|---|---|---|
| "I'll just use the API directly" | Replicate API changes; runner abstraction insulates your code | One integration point, not N scattered calls |
| "Docker is enough" | Docker lacks model versioning, caching, cost tracking | Runner adds observability and governance |
| "I don't need model routing" | Different models excel at different tasks | Route automatically; don't hardcode |
Trigger phrases:
-
"replicate runner"
-
"Run AI models on Replicate cloud API"
-
When running AI models without managing GPU infrastructure
-
When generating images, videos, or audio with state-of-the-art models
-
When deploying custom models to a cloud API
-
When chaining multiple AI models in a pipeline
When NOT to Use
- For local inference (use Ollama skills)
- For OpenAI-compatible endpoints (use OpenAI skills)
- For fine-tuning (use training-specific skills)
Overview
Access 1000+ AI models via Replicate API. Run Flux, Stable Diffusion, Whisper, and custom models with a single API call. Pay per second of compute.
Setup & Configuration
1. Get API Token
Sign up at replicate.com, then create an API token in your account settings.
2. Environment Variable
export REPLICATE_API_TOKEN=r8_xxxxxxxxxxxxxxxxxxxx
Or store in .env:
REPLICATE_API_TOKEN=r8_xxxxxxxxxxxxxxxxxxxx
3. Install SDK
Python:
pip install replicate
Node.js:
npm install replicate
4. SDK Initialization
Python:
import replicate
# Token auto-reads from REPLICATE_API_TOKEN env var
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 · 464 lines · 40 tokens per session scan A e4e9d822e491
replicate-runner is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 3,537 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
prism
Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.
audio-prompting
Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering.
video-prompting
Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining.
generation-diversity
Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls.
image-prompting
Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas.
image-search
Search the web for images (photos, logos, graphics) and download them with Typst embedding code. Use when the user needs real-world images, company logos, or existing graphics for documents.