bfm-develop

bfm-develop is a skill for Claude Code from babyworm/rtl-agent-team. It costs 53 tokens per session (2,096 once invoked), scanned A, original, MIT.

A skill for building SystemC TLM-2.0 bus functional models, which are software models that imitate hardware bus traffic. It supports AMBA interfaces such as AXI, AHB, and APB, plus DPI-C connections to SystemVerilog testbenches.

In plain words
What is it for?
It is for creating stimulus and checking models, early performance estimates, protocol verification, and hardware/software co-simulation.
Why use it?
It lets teams test protocols and estimate performance before the final hardware design exists, using faster software models.

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 It is for creating stimulus and checking models, early performance estimates, protocol verification, and hardware/software co-simulation.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/bfm-develop.svg)](https://agentmods.dev/skills/babyworm/rtl-agent-team/bfm-develop)
Your own site
<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/bfm-develop"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/bfm-develop.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,096 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 $0.00053 $0.02096
Opus 5 $0.00026 $0.01048
Sonnet 5 $0.00011 $0.00419
Haiku 4.5 $0.00005 $0.00210

Measured 4d ago against content hash e07ba4044624, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bfm-develop 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_bfm.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/bfm-develop/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<Use_When>

  • Phase 2 artifacts (docs/phase-2-architecture/architecture.md, refc/) are complete.
  • TLM models are needed for early performance estimation or protocol verification.
  • BFM is needed as stimulus/checker in a verification environment.
  • AMBA bus protocol modeling (AXI/AHB/APB) is required.
  • DPI-C co-simulation interface is needed for SystemVerilog testbenches. </Use_When>

<Do_Not_Use_When>

  • Architecture is not yet stable — a BFM built on a changing arch spec requires full rewrite.
  • Only simple unit tests are needed → use rtl-p4s-unit-test directly.
  • Pure software development without hardware interaction. </Do_Not_Use_When>

<Why_This_Exists> TLM models run orders of magnitude faster than RTL simulation, enabling early detection of protocol bugs and performance bottlenecks before RTL exists. The BFM also serves as the performance reference in rtl-p5s-perf-verify. LT transport is the default because it gives fast functional validation; AT non-blocking is reserved for timing-accurate pipelined modeling. </Why_This_Exists>

Prerequisites

  • docs/phase-2-architecture/architecture.md and io_definition.json present.
  • refc/ reference model built (needed for cross-phase functional consistency check).
  • SystemC 3.0+ and ARM AMBA-PV headers installed.

If missing: WARNING — proceed with available artifacts; note absent dependencies in smoke test result.

<Responsibility_Boundary>

  • Scripts handle build (cmake/make) and smoke-test execution via Bash CLI.
  • LLM handles TLM module design, protocol binding, and feature-coverage mapping.
  • Contract surface: port names must match io_definition.json exactly; functional output must match refc/ on shared test vectors. </Responsibility_Boundary>

Read the full file on GitHub · 131 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 · 131 lines · 53 tokens per session scan A e07ba4044624

Subscribe to this mod's changes

bfm-develop is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 14d ago), licensed MIT. It adds 53 tokens to every session and 2,096 once invoked, about $0.0003 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.