pollinations-setup

A setup command connects a Pollinations account to Claude Code, a tool for working with code from a command line. It opens a browser for login or accepts an existing API key, then saves the key locally.

In plain words
What is it for?
Use it to sign in to Pollinations from Claude Code and make the account’s generation tools available.
Why use it?
It avoids manually configuring authentication before using Pollinations generation tools. Usage is paid for with the account’s pollen credits.

Command

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.

agentmods
npx agentmods add commands/tolerable/pollinations-claude-code/pollinations-setup
Clone the repo
git clone --depth 1 https://github.com/Tolerable/pollinations-claude-code
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00115
Opus 5 $0.00000 $0.00057
Sonnet 5 $0.00000 $0.00023
Haiku 4.5 $0.00000 $0.00012

Measured 2d ago against content hash 84c75b331098, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pollinations-setup 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 2d 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.

commands/pollinations-setup.md · 17 lines

What it actually says

/pollinations-setup

Connect your Pollinations account to Claude Code using BYOP (Bring Your Own Pollen).

This opens your browser to log in at Pollinations. Once authorized, your API key is saved locally and all generation tools become available.

Your pollen credits fund usage — the plugin costs nothing to run.

Usage

Just type /pollinations-setup and follow the browser prompt.

If you already have an API key, you can pass it directly:

Use the pollinations_setup tool with api_key="your-key-here"
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. 2d ago First seen · 17 lines · 0 tokens per session scan A 84c75b331098

Subscribe to this mod's changes

pollinations-setup is a command published in the GitHub repository Tolerable/pollinations-claude-code (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 115 tokens. 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 2026-08-31.