replicate

replicate is a skill for Claude Code, Codex from ericrisco/rsc-harness. It costs 73 tokens per session (2,574 once invoked), scanned A, original, MIT.

A guide to running machine-learning models in production on Replicate, including synchronous and background jobs, webhooks, deployments, packaging, scaling, and GPU costs.

In plain words
What is it for?
Use it to run models from Python or JavaScript, package them with Cog, create private endpoints, handle webhook signatures, autoscale deployments, and control GPU spending.
Why use it?
It helps choose whether to wait for a result, poll for it, or receive a webhook, while avoiding request timeouts, unnecessary costs, and deployment mistakes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run models from Python or JavaScript, package them with Cog, create private endpoints, handle webhook signatures, autoscale deployments, and control GPU spending.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ericrisco/rsc-harness/replicate
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 ericrisco/rsc-harness --skill replicate
Clone the repo
git clone --depth 1 https://github.com/ericrisco/rsc-harness

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.

agentmods badge for replicate

README.md
[![agentmods](https://agentmods.dev/badge/skills/ericrisco/rsc-harness/replicate/github.svg)](https://agentmods.dev/skills/ericrisco/rsc-harness/replicate)
Your own site
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/replicate"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/replicate/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.

agentmods 80×15 button for replicate

Your own site · 80×15
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/replicate"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/replicate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,574 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.02574
Opus 5 $0.00036 $0.01287
Sonnet 5 $0.00015 $0.00515
Haiku 4.5 $0.00007 $0.00257

Measured 8d ago against content hash a0f8c4c44250, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

replicate 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/replicate/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Replicate platform operations

This skill is about how a model runs in production on Replicate — clients, async, deployments, Cog packaging, webhooks, scaling, and spend. It is the platform-engineering counterpart to image prompt craft. If the question is what prompt, aspect ratio, or model family produces a good image, that is replicate-images, not this skill. Here the mental model is: a prediction is a job. You either wait for it, poll it, or get pinged about it — and where it runs (shared cold pool vs a private warm deployment) is a cost-and-latency dial you set deliberately.

Pinned facts (verified 2026-06-02): Python client replicate 1.x (latest 1.0.7), Python 3.8+; JS client replicate on npm; auth via REPLICATE_API_TOKEN. A 2.0.0aN alpha exists on PyPI but is NOT the default — pin replicate>=1,<2 so a fresh install never silently pulls it.

Decision: how should this model run?

Pick the row by latency tolerance and whether your process can block. Do not default to run() for everything — a 10-minute job inside a web request will time out and burn a worker.

Pattern Latency Blocks your process? Cost shape Use when
replicate.run(...) seconds Yes — waits to completion per-prediction, shared pool interactive/quick calls, scripts, CLIs
predictions.create() + poll minutes Yes, but you control the loop per-prediction, shared pool long job, a worker can babysit it
predictions.create(webhook=...) minutes+ No — fire and forget per-prediction, shared pool long job, the request must return now
Deployment (private endpoint) low + steady depends on call style above warm floor + per-prediction sustained traffic, need warm/private/autoscale cap

Rule: if a human or HTTP request is waiting longer than a few seconds, do not block on run() — switch to predictions + webhook. Why: synchronous timeouts kill the request but the GPU job keeps running and billing.

Auth & install

Read the full file on GitHub · 211 lines

Files

What ships with it

6 files 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.

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.

  1. 8d ago First seen · 211 lines · 73 tokens per session scan A a0f8c4c44250

Subscribe to this mod's changes

replicate is a skill published in the GitHub repository ericrisco/rsc-harness (82 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 2,574 once invoked, about $0.0004 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 2026-09-03.