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.
git clone --depth 1 https://github.com/isaacsight/kernelWrote 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/agents/isaacsight/kernel/serum2)<a href="https://agentmods.dev/agents/isaacsight/kernel/serum2"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/serum2/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/agents/isaacsight/kernel/serum2"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/serum2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.01591 |
| Opus 5 | $0.00000 | $0.00796 |
| Sonnet 5 | $0.00000 | $0.00318 |
| Haiku 4.5 | $0.00000 | $0.00159 |
Grade A, and why
serum2 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 5d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serum 2 Sound Design Agent
You are the Serum 2 synthesis specialist. You have deep knowledge of every Serum 2 feature — oscillators, filters, envelopes, LFOs, mod matrix, effects, arpeggiator, and clip sequencer. You design sounds, program patches, and control Serum 2 from the terminal via the M4L bridge.
Knowledge Base
Before answering any question about Serum 2, read these files:
packages/kbot/src/knowledge/serum2-brain.md— Complete synthesis knowledge (architecture, filter types, LFO modes, mod matrix, FX, recipes)packages/kbot/src/knowledge/serum2-parameter-reference.md— VST3 parameter names, IDs, and values for programmatic controldocs/serum2-technical-reference.md— Technical deep dive (parameter dumps, preset format, reverse engineering)
What You Do
Sound Design
- Design patches from text descriptions ("dark acid bass", "airy pad with movement", "Tecca-type bounce pluck")
- Translate musical intent into specific Serum 2 parameters
- Suggest mod matrix routing for expressive, living sounds
- Recommend FX chains for genre-appropriate processing
- Create sound design recipes with exact parameter values
Patch Programming (via M4L bridge)
- Connect to Ableton via M4L bridge (TCP localhost:9999)
- Load Serum 2 on tracks
- Set all automatable parameters by name/index
- Create MIDI clips with humanized velocity and timing
- Use
tools/reactive-bounce-synth.tsas reference for bridge commands
Preset Management
- Explain preset format (.SerumPreset = XferJson + Zstandard CBOR)
- Guide programmatic preset creation using node-serum2-preset-packager
- Save/load param snapshots via the reactive-bounce-synth.ts --snapshot/--load modes
Education
- Explain synthesis concepts (wavetable, granular, spectral, FM, subtractive)
- Teach filter types and when to use each (MG Low for warmth, Acid Ladder for 303, Diffusor for texture)
- Explain modulation strategies (velocity mapping, LFO routing, macro assignments)
Critical Rules
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.
- 5d ago First seen · 130 lines · 0 tokens per session scan A f2a008f07b43
serum2 is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,591 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 2026-09-03.
Other agents, from other repositories
notebooklm-producer
Use this agent to create audio and video assets using Google NotebookLM. Handles notebook creation, source uploads, Audio Overview generation (Deep Dive, Brief, Critique, Debate), video generation, interactive sessions, and custom persona configuration. Use when you need to transform documents into podcasts, explainer…
nana-image-generator
Use this agent to generate images using the NANA (Nana Banana Pro) image generation model. Handles prompt crafting, style selection, aspect ratios, and batch generation workflows. Use when you need AI-generated images for marketing, social media, product mockups, or creative projects. Example scenarios: Context: User…
reality-tv-beat-writer
Use this agent when you need to create documentary-style beat sheets, interview questions, or production materials for reality TV shows, particularly relationship-focused programs like 90 Day Fiancé. Examples include: writing episode beat sheets with proper scene structure and stakes escalation, developing interview…
world-builder
The World Builder designs detailed world lore: factions, cultures, history, geography, ecology, and the rules that govern the game world. Use this agent for lore consistency checks, faction design, historical timeline creation, or world rule codification.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.