Pollinations is an open-source generative AI platform that lets people create or access AI-generated text, images, audio, and video through its playground, applications, and APIs. It is used by makers and developers who want to build creative tools or integrate generative models into their projects. The catalogue includes skills, commands, agents, and other add-ons for working with Pollinations.
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 pollinations/pollinations --skill polli-cligit clone --depth 1 https://github.com/pollinations/pollinationsWrote 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/pollinations/pollinations/polli-cli)<a href="https://agentmods.dev/skills/pollinations/pollinations/polli-cli"><img src="https://agentmods.dev/badge/skills/pollinations/pollinations/polli-cli/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/pollinations/pollinations/polli-cli"><img src="https://agentmods.dev/badge/skills/pollinations/pollinations/polli-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 162 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 163 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 164 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 174 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 175 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 211 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00066 | $0.07615 |
| Opus 5.5 | $0.00026 | $0.03046 |
| Sonnet 5.5 | $0.00013 | $0.01523 |
| Haiku 4.5 | $0.00007 | $0.00762 |
Grade A, and why
polli 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 today.
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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
polli — Pollinations CLI
Thin wrapper around gen.pollinations.ai. Generates images, text, audio, video; transcribes speech; manages API keys, usage, quests, agents, and invite-only my-models.
If polli is not installed, run npm i -g @pollinations/cli@latest (provides the polli binary).
When to use this skill
- User asks to generate an image / text / audio / video via pollinations
- User mentions polli, pollinations, pollen, pollinations.ai
- User wants to transcribe speech or run TTS
- User asks about their pollen balance, usage, or API keys
- User wants to browse or filter available models
- User wants to inspect quests or manage invite-only my-models
- User wants to create or update a hosted prompt agent
For agent-assisted login, use polli --json auth login --no-browser. Read stderr while the command runs and show the user the verification URL and user code so they can review access. On approval, stdout contains one JSON result: {"authenticated":true}. Tokens are stored locally and never included in that result.
Quick reference
| Intent | Command |
|---|---|
| Log in once | polli auth login |
| Agent-assisted login | polli --json auth login --no-browser |
| Store an existing key | printf '%s' "$POLLINATIONS_API_KEY" | polli auth login --with-token |
| Generate image | polli gen image "<prompt>" --output out.png |
| Generate text | polli gen text "<prompt>" |
| Text with stdin as context | echo "<ctx>" | polli gen text "<question>" |
| Describe an image (vision) | polli gen text "what is this?" --image <url> |
| One-shot TTS | polli gen audio "<text>" --output speech.mp3 |
| Speak out loud | polli gen audio "<text>" --play (uses afplay on macOS; ffplay/mpv/mpg123 on Linux) |
| Generate video | polli gen video "<prompt>" --output out.mp4 |
| Generate a 3D model | polli gen 3d "<prompt>" --output out.glb (or --image <url> for image-only models) |
| Embed text | polli gen embeddings "<text>" ["<text2>" ...] (one vector per line; also reads stdin) |
| Change a voice | polli gen voice-change talk.mp3 --voice nova |
| Isolate speech | polli gen isolate interview.mp4 (strips music/noise) |
| Speech + character timings | polli gen audio "<text>" --timestamps (also writes speech.mp3.json) |
| Transcribe audio | polli gen transcribe path/to.mp3 |
| Upload a local file | polli upload path/to.png (prints public URL) |
| List all models | polli models |
| Filter models by type | polli models --type image (text, image, audio, video, 3d, embedding) |
| Model health + latency | polli models --stats (default 60m, --window <min>) |
| Check balance | polli usage |
| Developer earnings | polli earnings (--days <n>) |
| List your quests + claim state | polli quests (filters: --open --claimable --claimed --coming-soon) |
| Manage prompt agents | polli agents list |
| Manage invite-only community models | polli my-models list |
| Update the CLI | polli update (global installs only; npx/local get instructions) |
| Connect a coding harness to Pollinations | polli harness <bloom|dsh|hermes|opencode|openclaw|pi|prime|tgpt> on (available adapters: polli harness --help) |
| Start a Linux sandbox (alpha) | polli sandbox create (--timeout <seconds> to keep it running without ssh, 0 until you pause or kill it; pollinations-large as the template for 4 vCPU and 8 GB; then list, logs <id>, timeout <id> <seconds>, pause <id>, kill <id>); the default template comes logged in, with the coding harnesses |
| ssh / scp / rsync into a sandbox | ssh <sandbox-id>.polli. Port forwarding (ssh -L 3000:localhost:3000 <sandbox-id>.polli) and VS Code Remote-SSH work. An open connection keeps the sandbox running and paid; it pauses 15–20 minutes after the last one closes (5–10 on Windows) |
| Machine-readable output | append --json to any command |
What ships with it
60 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.
- bin/polli.js 47 B runs code
- package-lock.json 103 KB
- package.json 1.8 KB
- README.md 10 KB
- src/commands/agents.test.ts 2.3 KB runs code
- src/commands/agents.ts 9.6 KB runs code
- src/commands/auth.test.ts 7.0 KB runs code
- src/commands/auth.ts 9.3 KB runs code
- src/commands/docs.test.ts 3.5 KB runs code
- src/commands/docs.ts 3.9 KB runs code
- src/commands/earnings.test.ts 840 B runs code
- src/commands/earnings.ts 2.1 KB runs code
- src/commands/gen/audio.test.ts 9.9 KB runs code
- src/commands/gen/audio.ts 6.1 KB runs code
- src/commands/gen/chat.test.ts 11 KB runs code
- src/commands/gen/chat.ts 9.5 KB runs code
- src/commands/gen/embeddings.test.ts 4.1 KB runs code
- src/commands/gen/embeddings.ts 2.7 KB runs code
- src/commands/gen/image.test.ts 1.9 KB runs code
- src/commands/gen/image.ts 3.4 KB runs code
- src/commands/gen/index.ts 1.1 KB runs code
- src/commands/gen/isolate.test.ts 3.1 KB runs code
- src/commands/gen/isolate.ts 2.0 KB runs code
- src/commands/gen/model3d.test.ts 4.9 KB runs code
- src/commands/gen/model3d.ts 3.5 KB runs code
- src/commands/gen/text.test.ts 5.5 KB runs code
- src/commands/gen/text.ts 10.0 KB runs code
- src/commands/gen/transcribe.ts 1.8 KB runs code
- src/commands/gen/video.test.ts 1.7 KB runs code
- src/commands/gen/video.ts 2.9 KB runs code
- src/commands/gen/voice-change.test.ts 3.2 KB runs code
- src/commands/gen/voice-change.ts 2.4 KB runs code
- src/commands/harness.ts 3.2 KB runs code
- src/commands/keys.test.ts 5.4 KB runs code
- src/commands/keys.ts 11 KB runs code
- src/commands/mcp.ts 5.7 KB runs code
- src/commands/models.ts 7.7 KB runs code
- src/commands/my-models.test.ts 8.4 KB runs code
- src/commands/my-models.ts 20 KB runs code
- src/commands/quests.test.ts 2.1 KB runs code
- src/commands/quests.ts 4.5 KB runs code
- src/commands/sandbox/bootstrap.sh 2.8 KB runs code
- src/commands/sandbox/e2b.ts 2.6 KB runs code
- src/commands/sandbox/index.test.ts 12 KB runs code
- src/commands/sandbox/index.ts 9.1 KB runs code
- src/commands/sandbox/ssh.ts 7.8 KB runs code
- src/commands/stats.ts 611 B runs code
- src/commands/update.test.ts 1.8 KB runs code
- src/commands/update.ts 5.1 KB runs code
- src/commands/upload.test.ts 2.9 KB runs code
- src/commands/upload.ts 2.8 KB runs code
- src/commands/usage.test.ts 9.5 KB runs code
- src/commands/usage.ts 14 KB runs code
- src/commands/validation.test.ts 7.8 KB runs code
- src/harnesses/bloom.test.ts 2.7 KB runs code
- src/harnesses/bloom.ts 3.3 KB runs code
- src/harnesses/claude-code.test.ts 6.6 KB runs code
- src/harnesses/claude-code.ts 4.9 KB runs code
- src/harnesses/codex.test.ts 11 KB runs code
- src/harnesses/codex.ts 14 KB runs code
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.
- today Changed 0c8e2b186791
- yesterday Changed · +3 lines 7ed8f67afa58
- 2d ago Changed 23f23887f2d5
- 3d ago Changed · +3 lines 8415491b2f16
- 4d ago Changed d0c193deb2f6
- 6d ago Changed · +1 lines 102fc3a14f51
- 7d ago Changed e7b78170feb8
- 9d ago Changed 6d410ac59826
- 11d ago Changed 3a896196dc8e
- 13d ago First seen · 306 lines · 66 tokens per session scan A be4fbbae1b2f
polli is a skill published in the GitHub repository pollinations/pollinations (5,212 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 7,615 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 2026-08-30.
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.
img2threejs
Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
tao-finetune-kumo-anomaly
Kumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune Kumo-Anomaly", "run Kumo-Anomaly inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune Kumo-Anomaly", "use performanomalyanalysiswithdiffusion"…
protein-structure-design-boltzgen
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For structure…