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 babyworm/rtl-agent-team --skill domain-consultgit clone --depth 1 https://github.com/babyworm/rtl-agent-teamWrote 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/babyworm/rtl-agent-team/domain-consult)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/domain-consult"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/domain-consult/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/babyworm/rtl-agent-team/domain-consult"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/domain-consult.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 | $0.00035 | $0.02499 |
| Opus 5 | $0.00017 | $0.01249 |
| Sonnet 5 | $0.00007 | $0.00500 |
| Haiku 4.5 | $0.00003 | $0.00250 |
Grade A, and why
domain-consult 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 8d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- User has a domain-specific question (codec algorithms, video processing, signal processing, hardware protocols)
- Choosing the wrong expert would give a shallow answer
- Multiple domains may be relevant and the best expert needs to be selected </Use_When>
<Do_Not_Use_When>
- Question is about RTL coding style (ask rtl-coder directly)
- Question is about synthesis or timing (use rtl-synth-check or timing-advisor directly)
- Implementation work is needed, not consultation </Do_Not_Use_When>
<Why_This_Exists> The project has multiple domain experts (6 codec sub-domain specialists, a codec chief, video processing, and protocol experts). Routing to the wrong expert wastes tokens and produces shallow answers. This skill reads the query and selects the best match before delegating. </Why_This_Exists>
<Execution_Policy>
- Classify the query into a domain based on keywords and topic
- Delegate to exactly one primary expert (Opus for deep analysis, Sonnet for lookups)
- If multiple domains apply, delegate to both in parallel and merge answers
- For cross-domain codec questions, delegate to vcodec-chief-standard-expert (or relevant 2 sub-domain experts in parallel)
- Return expert answer verbatim, do not summarize or filter </Execution_Policy>
<Routing_Table>
| Domain Keywords | Expert Agent | Notes |
|---|---|---|
| NAL, slice header, CABAC, CAVLC, entropy coding, DPB, bitstream, binarization, context model, Exp-Golomb | vcodec-syntax-entropy-expert | HLS parsing, entropy engine, DPB management |
| intra prediction, angular mode, planar mode, DC mode, intra reference sample, intra mode decision, neighboring sample, intra smoothing | vcodec-intra-pred-expert | Intra prediction modes, reference sample construction, mode-dependent filtering |
| motion estimation, ME, search algorithm, IME, FME, TZ search, diamond search, MV prediction, AMVP, merge mode, search range, reference frame selection | vcodec-me-expert | ME search algorithms, MV prediction (AMVP/merge), reference frame management |
| motion compensation, MC, sub-pel interpolation, half-pel, quarter-pel, bi-prediction, weighted prediction, reference block fetch, interpolation filter | vcodec-mc-expert | Sub-pixel interpolation filters, bi-prediction weighting, weighted prediction |
| DCT, DST, quantization, RDOQ, fixed-point, scaling matrix, QP, transform, inverse transform, butterfly, dequantization, coefficient, scaling list | vcodec-transform-quant-expert | Transform, quantization, fixed-point arithmetic |
| deblocking, SAO, in-loop filter, boundary strength, reconstruction, filter decision, edge offset, band offset, sample adaptive offset | vcodec-filter-recon-expert | Deblocking filter, SAO, reconstruction path |
| cross-block, cross-block dependency, pipeline dependency, architecture-ready, architecture-ready assessment, codec domain coordination, codec overview, block interaction, data flow between blocks | vcodec-chief-standard-expert | Cross-block coordination, multi-block dependency analysis |
| codec pipeline, encoder/decoder architecture, datapath, throughput, latency, SRAM organization | vcodec-architecture-expert | Architecture-level codec design decisions |
| throughput, memory bandwidth, cycles per block, macroblock rate, CTU rate, DPB sizing, line buffer sizing, pipeline depth, parallelism degree, performance budget, frames per second, resolution target | video-processing-expert | Codec HW performance analysis (throughput, bandwidth, pipeline) |
| color space conversion, RGB to YUV, YUV to RGB, BT.601, BT.709, BT.2020, chroma subsampling, chroma upsampling, 4:2:0, 4:2:2, 4:4:4, bit depth conversion, 8-bit to 10-bit, Bayer demosaic, color format, limited range, full range, V4L2, fourcc, pixelformat, bytesperline, sizeimage, single-planar, multi-planar, NV12M, tiled format, storage layout | vproc-color-format-expert | Color format conversion + V4L2 storage semantics (FOURCC/plane/stride/sizeimage) |
| denoise, noise reduction, bilateral filter, NLM, temporal noise reduction, 3DNR, motion adaptive, spatial filter, Gaussian filter, noise model, AWGN, shot noise | vproc-denoise-expert | Spatial/temporal noise reduction for video HW |
| HDR, tone mapping, PQ curve, HLG, gamma correction, OETF, EOTF, sRGB, image scaling, resampling, bilinear, bicubic, Lanczos, edge enhancement, sharpening, unsharp mask, ISP pipeline, image signal processing | vproc-image-processing-expert | HDR, gamma, scaling, sharpening, ISP pipeline |
| AXI, AHB, APB, PCIe, USB, Ethernet, bus protocol, handshake, transaction | protocol-checker | Bus protocol rules and timing |
| </Routing_Table> |
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.
- 8d ago First seen · 164 lines · 35 tokens per session scan A 559bf973afc5
domain-consult is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 18d ago), licensed MIT. It adds 35 tokens to every session and 2,499 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
readable-verilog-generator
Use when creating, writing, reviewing, annotating, repairing, refactoring, or validating readable Verilog RTL, including synthesizable Verilog-2001 .v files, existing-RTL analysis, semantic comment annotation, testbench scaffold planning, ASIC-quality review, local or remote Vivado/xsim validation, evidence-backed…
hardware-saas-gtm
🇺🇸 Hardware + SaaS GTM Playbook — End-to-end go-to-market for consumer hardware products with software subscription models. Covers crowdfunding engineering (Kickstarter/Indiegogo/Makuake), KOL matrix for physical products, hardware PMF validation metrics, device-as-funnel subscription design, localization entry…
step-parts
Find, evaluate, and download low-level common standard CAD parts from step.parts, such as screws, bolts, nuts, washers, bearings, standoffs, electronics parts, motors, connectors, and other off-the-shelf components. Use when Codex needs to search the hosted step.parts catalog, resolve fuzzy part names, standards…
system-info
A skill for checking computer hardware, system status, running processes, and available disk space.
hdldiagzero
Generate validated SVG block diagrams for HDL/RTL/FPGA/SoC designs. Use when asked to draw, diagram, sketch, render, or visualize Verilog, SystemVerilog, VHDL, Vivado BD, or LiteX architecture. Produces JSON specs plus SVGs, color-codes clock domains, distinguishes AXI/MM/Lite/Stream and TileLink, and hides…