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 ericrisco/rsc-harness --skill replicate-imagesgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/replicate-images)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/replicate-images"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/replicate-images/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/ericrisco/rsc-harness/replicate-images"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/replicate-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.03306 |
| Opus 5.5 | $0.00034 | $0.01322 |
| Sonnet 5.5 | $0.00017 | $0.00661 |
| Haiku 4.5 | $0.00008 | $0.00331 |
Grade A, and why
replicate-images 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replicate image generation & prompt craft
This skill is the image layer on top of Replicate: how to call an image model from code and how
to write a prompt that the specific model family actually obeys. Two competencies braided together —
mechanics (run path, output handling, levers, image inputs) and prompt shape per family
(Gemini/Nano-Banana wants prose, Flux wants dense description, gpt-image wants instructions). If the
question is platform plumbing — auth, billing, deployments, webhooks, running an LLM or audio model —
that is replicate, not this skill.
Pinned facts (verified 2026-06-02). Slugs and parameter names are the load-bearing details that make
code run, and they drift — the full per-model schema lives in references/models.md so this file
stays evergreen. Confirm any exact slug/param on the model page before quoting it as fact.
First move
export REPLICATE_API_TOKEN=r8_... # both clients read this automatically
npm install replicate # Node; pip install replicate for Python
import Replicate from "replicate";
const replicate = new Replicate(); // reads REPLICATE_API_TOKEN from env
const output = await replicate.run("google/nano-banana-2", {
input: { prompt: "a red ceramic mug on a sunlit wooden table, soft morning light" },
});
console.log(output[0].url()); // hosted URL of the first image
Rule: do not hand-build the token into the client — let new Replicate() read the env var. Why: a
hardcoded token leaks into git and logs. Python is the same shape: replicate.run("google/nano-banana-2", input={"prompt": ...}).
Pick the model
Pick by the dominant requirement, not by hype. Full input schemas and rough cost tiers per model are
in references/models.md.
| Need | Model slug | Why |
|---|---|---|
| Best editing + multi-image composition | google/nano-banana-2 |
Gemini 3.1 Flash Image; up to 14 reference images, conversational edits |
| Top-quality / hard compositions, budget allows | google/nano-banana-pro |
Gemini 3 Pro Image; ~2x the NB2 cost at 1K |
| Dense photoreal, fine control of light/lens | black-forest-labs/flux-1.1-pro |
rewards rich descriptive prompts; exposes seed, size |
| Fast/cheap draft loop | black-forest-labs/flux-schnell |
sync-optimized, lowest latency for iterating |
| Strict instruction-following + crisp text | openai/gpt-image-1 (OpenAI on Replicate) |
follows complex instructions; needs your own OpenAI key wired in |
| Up-to-4K + batch/sequential output | bytedance/seedream-4 |
unified text-to-image and editing, multi-reference |
What ships with it
5 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.
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 · 242 lines · 84 tokens per session scan A ed5d3a167aa9
replicate-images is a skill published in the GitHub repository ericrisco/rsc-harness (267 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 3,306 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
imagethis
Generate an AI image from a text prompt and load it into context, in one step. Routes to FLUX / SDXL / Ideogram / Recraft (Replicate) or gpt-image-2 (OpenAI). Use when a message starts with "imagethis:", or the user says "generate an image", "make a picture/logo of…", or "draw…".
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
setting-up-a-project
Use when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinary work in an already-specced project.