ref-model

ref-model is a skill for Claude Code from babyworm/rtl-agent-team. It costs 38 tokens per session (2,046 once invoked), scanned A, original, MIT.

A C reference implementation of a video-codec algorithm used as a bit-exact baseline, with estimates of external memory traffic and bandwidth needs.

In plain words
What is it for?
Use it to build or update a golden model, compare results with H.264 or H.265 reference software, and explore datapath widths or memory bandwidth.
Why use it?
Building the model early exposes unclear requirements and provides an independent expected result for later RTL verification.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the rtl-agent-team plugin — 47 skills, 99 agents, 6 hooks shipped together

Good fit Use it to build or update a golden model, compare results with H.264 or H.265 reference software, and explore datapath widths or memory bandwidth.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/babyworm/rtl-agent-team/ref-model
Install

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.

Any agent
npx skills add babyworm/rtl-agent-team --skill ref-model
Clone the repo
git clone --depth 1 https://github.com/babyworm/rtl-agent-team

Made for: Claude Code.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

Wrote 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.

agentmods badge for ref-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/ref-model.svg)](https://agentmods.dev/skills/babyworm/rtl-agent-team/ref-model)
Your own site
<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>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash d11b3fff3caa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_ref_model.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/ref-model/SKILL.md · 135 lines

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.json is current — avoid regenerating.
  • Only a quick algorithm question is needed → use domain-consult instead. </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.json present with REQ-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 Makefile targets.
  • LLM handles algorithm implementation, feature-coverage mapping, and spec-gap escalation.
  • Contract surface: ext_mem_read/write abstraction layer + REQ-F-* coverage table. </Responsibility_Boundary>

Read the full file on GitHub · 135 lines

Changes

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.

  1. 4d ago First seen · 135 lines · 38 tokens per session scan A d11b3fff3caa

Subscribe to this mod's changes

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.