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 agentmods add skills/pollinations/pollinations/web-researchnpx skills add pollinations/pollinations --skill web-researchgit clone --depth 1 https://github.com/pollinations/pollinationsWhat 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 | $0.00039 | $0.00398 |
| Opus 5 | $0.00019 | $0.00199 |
| Sonnet 5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
web-research 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` What it actually says
Web Research
Available Models
- gemini-search — Google Gemini with web search grounding (default)
- perplexity-fast — Perplexity AI, faster (default)
- perplexity — Perplexity AI
- nomnom — NomNom search model
By default, queries both gemini-search and perplexity-fast in parallel.
Requirements
curl
Authentication
Set an API key in an environment variable (preferred):
export POLLINATIONS_API_KEY="YOUR_KEY"
Or create a local .env file at .claude/skills/web-research/.env:
POLLINATIONS_API_KEY="YOUR_KEY"
If POLLINATIONS_API_KEY is not set, the script will prompt for a key (input hidden).
Quick usage
.claude/skills/web-research/scripts/web-research.sh "What is pollinations.ai?"
Choose a model:
.claude/skills/web-research/scripts/web-research.sh --model perplexity-fast "Fact-check this claim with sources"
Compare multiple models:
.claude/skills/web-research/scripts/web-research.sh --models gemini-search,perplexity-fast,nomnom "Compare answers"
Run multi-model in parallel:
.claude/skills/web-research/scripts/web-research.sh --models gemini-search,perplexity-fast --parallel "Compare answers"
Notes
- Uses
https://gen.pollinations.ai/v1/chat/completions - Sends
Authorization: Bearer <key>
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.
- 2d ago First seen · 65 lines · 39 tokens per session scan A 915e33075d47
web-research is a skill published in the GitHub repository pollinations/pollinations (5,013 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 398 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 2026-08-30.
Other skills, from other repositories
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
model-integration
Use when adding a new model or pipeline to diffusers, setting up file structure for a new model, converting a pipeline to modular format, or converting weights for a new version of an already-supported model.
custom-blocks
Use when the user has written (or wants to write) a ModularPipelineBlocks subclass in a local Python file and needs to package it into a Hub-uploadable directory. Covers the workflow from a single block.py file to a published custom-block repo that consumers can load via ModularPipeline.frompretrained( …
diffusers-cli
Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF Sandbox hardware via --remote, introspect a pipeline's input schema before calling it, or attach a LoRA at inference time. Prefer this over writing ad-hoc Python scripts for…
self-review
Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the @claude CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity, flagging what to fix before submitting (blocking issues + dead code)…