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 truthanb/patchwork-deepmind --skill deepmind-parameter-guidegit clone --depth 1 https://github.com/truthanb/patchwork-deepmindWrote 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/truthanb/patchwork-deepmind/deepmind-parameter-guide)<a href="https://agentmods.dev/skills/truthanb/patchwork-deepmind/deepmind-parameter-guide"><img src="https://agentmods.dev/badge/skills/truthanb/patchwork-deepmind/deepmind-parameter-guide/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/truthanb/patchwork-deepmind/deepmind-parameter-guide"><img src="https://agentmods.dev/badge/skills/truthanb/patchwork-deepmind/deepmind-parameter-guide.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 | $0.00045 | $0.01546 |
| Opus 5.5 | $0.00018 | $0.00618 |
| Sonnet 5.5 | $0.00009 | $0.00309 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
deepmind-parameter-guide 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP note:
describe_paramreturns ranges, units, and enum labels for any parameter.set_param/set_paramsacceptvalue(0..1),rawValue, orlabel. This skill focuses on the why and what it sounds like — things the tools can't tell you.
Start with recipes.md for complete sound-design examples, then read individual sections for deeper context on a specific area.
Sections
| Section file | Covers |
|---|---|
| recipes.md | Non-obvious parameter interactions — full examples with values |
| oscillators.md | OSC 1 (saw/square/PWM), OSC 2 (pitch/tone mod/sync), noise, waveform enables |
| filter.md | VCF cutoff, resonance, 2/4-pole, env depth/polarity/velocity, LFO mod, key tracking, HPF, bass boost |
| envelopes.md | VCA/VCF/MOD envelope ADSR, trigger modes, per-stage curve shaping |
| lfos.md | LFO 1 & 2 rate, delay, shape, key/arp sync, phase/mono, slew rate, clock divide |
| vca.md | VCA level, envelope depth, velocity sensitivity, pan spread |
| mod-matrix.md | 8 mod busses: 24 sources, 132 destinations, bipolar depth, meta-modulation, FX modulation |
| arp-sequencer.md | Arpeggiator on/off, mode, rate, clock divider, gate, hold, pattern, swing, octaves; control sequencer enable, clock, length, swing, key/loop, slew, step values; ARP settings |
| effects.md | FX architecture (4 slots, routing, NRPNs), master effects table (35 types), links to category detail files |
| effects/reverbs.md | 13 reverb effects: TC-DeepVRB, AmbVerb, RoomRev, VintageRev, HallRev, ChamberRev, PlateRev, RichPltRev, GatedRev, Reverse, ChorusVerb, DelayVerb, FlangVerb |
| effects/delays.md | 6 delay effects: Delay, 3TapDelay, 4TapDelay, T-RayDelay, DecimDelay, ModDlyRev |
| effects/creative.md | 8 creative effects: Chorus, Chorus-D, Flanger, Phaser, MoodFilter, DualPitch, VintgPitch, RotarySpkr |
| effects/processing.md | 8 processing effects: MidasEQ, Enhancer, FairComp, MulBndDist, RackAmp, EdisonEX1, AutoPan, NoiseGate |
| playing-controls.md | Performance control index: pitch bend, mod wheel, aftertouch, velocity, expression pedal → parameter cross-references and setup recipes |
| global-settings.md | Global menu reference (no NRPNs): MIDI connectivity, keyboard curves, pedal modes, sustain/gate, panel, calibration |
What ships with it
16 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.
- sections/arp-sequencer.md 12 KB
- sections/effects.md 9.3 KB
- sections/effects/creative.md 12 KB
- sections/effects/delays.md 9.2 KB
- sections/effects/processing.md 11 KB
- sections/effects/reverbs.md 18 KB
- sections/envelopes.md 6.5 KB
- sections/filter.md 6.1 KB
- sections/global-settings.md 6.1 KB
- sections/lfos.md 9.1 KB
- sections/mod-matrix.md 16 KB
- sections/oscillators.md 5.2 KB
- sections/playing-controls.md 6.8 KB
- sections/recipes.md 7.6 KB
- sections/vca.md 4.4 KB
- sections/voice-config.md 12 KB
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.
- 1mo ago First seen · 70 lines · 45 tokens per session scan A c5b4b590dfc9
deepmind-parameter-guide is a skill published in the GitHub repository truthanb/patchwork-deepmind (3 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 1,546 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
apitap
ApiTap gives AI agents cheap access to web data through three layers.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…