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 ref-modelgit 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/ref-model)<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/ref-model"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/ref-model.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.02046 |
| Opus 5 | $0.00019 | $0.01023 |
| Sonnet 5 | $0.00008 | $0.00409 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
ref-model 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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- Phase 1 artifacts are complete and a reference model does not yet exist.
- Reference model needs updating after a spec change.
- A conformance baseline is needed before RTL verification can begin.
- Bandwidth or datapath-width exploration is required.
- An independent quality gate is needed before declaring the model a verification oracle. </Use_When>
<Do_Not_Use_When>
- Reference model already exists and
conformance_report.jsonis current — avoid regenerating. - Only a quick algorithm question is needed → use
domain-consultinstead. </Do_Not_Use_When>
<Why_This_Exists>
Writing the reference model before RTL forces algorithm understanding and exposes spec ambiguities before silicon commitment. Bitexact match against JM/HM is the industry-standard acceptance criterion. The model doubles as a bandwidth analysis tool by routing all external memory traffic through ext_mem_read/ext_mem_write, enabling memory-bandwidth estimation without RTL.
</Why_This_Exists>
Prerequisites
docs/phase-1-research/iron-requirements.jsonpresent withREQ-F-*items.- JM 19.0 (H.264) or HM 16.20 (H.265) installed and on
PATH.
If missing: WARNING — proceed with available artifacts; feature coverage step will note absent requirements file.
<Responsibility_Boundary>
- Scripts handle build, bitexact comparison, and bandwidth measurement via
Makefiletargets. - LLM handles algorithm implementation, feature-coverage mapping, and spec-gap escalation.
- Contract surface:
ext_mem_read/writeabstraction layer +REQ-F-*coverage table. </Responsibility_Boundary>
What ships with it
13 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.
- examples/README.md 2.0 KB
- examples/sat_add/.gitignore 108 B
- examples/sat_add/expected_run_report.json 476 B
- examples/sat_add/refc/include/sat_add_ref.h 471 B
- examples/sat_add/refc/Makefile 449 B
- examples/sat_add/refc/sat_add_ref.c 1.9 KB
- references/.gitkeep 0 B
- references/ref-model-conventions.md 3.4 KB
- scripts/run_ref_model.py 9.6 KB runs code
- templates/dpi_wrapper.h 1.4 KB
- templates/Makefile 1.2 KB
- templates/ref_model_header.h 2.0 KB
- templates/ref_model_main.c 3.7 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.
- 4d ago First seen · 135 lines · 38 tokens per session scan A d11b3fff3caa
ref-model is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 14d ago), licensed MIT. It adds 38 tokens to every session and 2,046 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
tuyaopen/usr-board
A workflow for adding a custom peripheral to a TuyaOpen project without changing the software development kit. A peripheral is an attached hardware device, and a TDD is a hardware driver interface used to control it.
vtestgen
Scaffold a Makefile-driven, CPU-bus-controlled testbench project for an IP and generate a comprehensive set of self-checking testcases, validate each with make, and write a testcase list.
vtestrun
Run all IP-level testcases from tclist.md through the bench Makefile, capture results, and write per-failure issue reports with no fix suggestions.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.