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 xg-gh-25/SwarmAI --skill s_pollinategit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_pollinate)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_pollinate"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_pollinate/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/xg-gh-25/swarmai/s_pollinate"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_pollinate.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 | $0.00096 | $0.00295 |
| Opus 5 | $0.00048 | $0.00148 |
| Sonnet 5 | $0.00019 | $0.00059 |
| Haiku 4.5 | $0.00010 | $0.00030 |
Grade A, and why
pollinate 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 11d 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.
What it actually says
Pollinate -- Swarm Media Value Delivery Engine
Your message, their attention, the right format.
Read INSTRUCTIONS.md before proceeding.
Quick Start
Tell your agent: "Pollinate: [topic]" or "Make a video about [topic]"
Verification
Before marking a Pollinate run complete, show evidence for each:
- REPORT.md generated -- saved to
content/{name}/REPORT.md - All 9 stages executed -- EVALUATE through REFLECT
- Confidence score calculated -- breakdown shown
- Decision log complete -- every decision classified (mechanical/taste/judgment)
- Studio preview reviewed -- user approved before 4K render
- Platform specs validated --
check_specs.pypassed for all target platforms
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.
- brand/assets/bgm/calm-piano.mp3 4814 KB
- brand/assets/logo/qr-github-dark-on-light.png 9.6 KB
- brand/assets/logo/qr-github-light-on-dark.png 9.6 KB
- brand/assets/logo/qr-github.png 9.6 KB
- brand/content_principles.md 5.2 KB
- brand/directions/d1-obsidian.yaml 3.5 KB
- brand/directions/d2-paper.yaml 3.5 KB
- brand/directions/d3-ink.yaml 3.7 KB
- brand/directions/d4-neon.yaml 3.9 KB
- brand/directions/d5-morandi.yaml 4.3 KB
- brand/identity.yaml 3.2 KB
- brand/poster_design_system.md 18 KB
- brand/tone_guide.md 4.0 KB
- channels/bilibili.yaml 1.3 KB
- channels/douyin.yaml 947 B
- channels/weixin_video.yaml 1.1 KB
- channels/xiaohongshu.yaml 1.2 KB
- channels/youtube.yaml 1.2 KB
- INSTRUCTIONS.md 94 KB
- phonemes.json 9.6 KB
- prefs_schema.json 15 KB
- references/design-guide.md 2.6 KB
- references/platform-adaptive.md 6.1 KB
- references/platform-specs.md 2.7 KB
- REVIEW_PATTERNS.md 5.5 KB
- scripts/brand_chart.py 5.0 KB runs code
- scripts/check_prereqs.py 1.9 KB runs code
- scripts/check_rpv.py 12 KB runs code
- scripts/check_specs.py 9.8 KB runs code
- scripts/convergence_gate.py 10 KB runs code
- scripts/cross_format_check.py 12 KB runs code
- scripts/deck_notes_injector.py 11 KB runs code
- scripts/evaluate_topic.py 5.4 KB runs code
- scripts/font_link_backfill.py 7.6 KB runs code
- scripts/format_recommend.py 28 KB runs code
- scripts/generate_shorts.py 22 KB runs code
- scripts/generate_tts.py 11 KB runs code
- scripts/geo_score.py 12 KB runs code
- scripts/get_pref.py 845 B runs code
- scripts/log_publish.py 2.5 KB runs code
- scripts/migrate_prefs.py 5.0 KB runs code
- scripts/p2_scan.py 4.3 KB runs code
- scripts/pollinate_validator.py 16 KB runs code
- scripts/pptx_to_deck.py 7.2 KB runs code
- scripts/publish_dashboard.py 18 KB runs code
- scripts/publish_meta.py 8.7 KB runs code
- scripts/publish_to_pages.py 15 KB runs code
- scripts/recommend_systems.py 9.7 KB runs code
- scripts/render_style_thumbnails.py 11 KB runs code
- scripts/resolve_backend.py 264 B runs code
- scripts/topic_backlog.py 9.7 KB runs code
- scripts/tts/__init__.py 43 B runs code
- scripts/tts/backends/__init__.py 7.1 KB runs code
- scripts/tts/backends/azure.py 3.1 KB runs code
- scripts/tts/backends/base.py 469 B runs code
- scripts/tts/backends/edge.py 3.2 KB runs code
- scripts/tts/backends/polly.py 17 KB runs code
- scripts/tts/phonemes.py 5.9 KB runs code
- scripts/tts/sections.py 6.7 KB runs code
- scripts/tts/srt.py 4.8 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.
- 11d ago First seen · 29 lines · 96 tokens per session scan A af0b74caac04
pollinate is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 295 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…
threejs-world-generation
Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…
dashscope
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.