agentmods.dev

simulation

A UVM simulation skill turns an approved hardware verification plan into a running testbench and executes its regression and coverage checks. UVM is a standard way to organize automated tests for digital hardware.

In plain words
What is it for?
It is for building and running hardware testbenches from an approved plan, then completing simulation and coverage runs.
Why use it?
It provides a controlled way to run the planned checks and determine whether the module meets its verification goals.

Skill for Claude CodeCodex

4 2d ago A scan 34 tokens original MIT
View the source file chipweaver/veripower
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.

agentmods
npx agentmods add skills/chipweaver/veripower/simulation
Any agent
npx skills add chipweaver/veripower --skill simulation
Clone the repo
git clone --depth 1 https://github.com/chipweaver/veripower

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.03138
Opus 5 $0.00017 $0.01569
Sonnet 5 $0.00007 $0.00628
Haiku 4.5 $0.00003 $0.00314

Measured yesterday against content hash d660d8cdaae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simulation 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 yesterday.

The scan reads SKILL.md. This mod also ships 17 executable files (scripts/sim/__init__.py, scripts/sim/__main__.py, scripts/sim/_boundary.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/simulation/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UVM Simulation

Your sole responsibility: turn this module's approved verification plan into a running UVM testbench, establish that the checks in it verify what the plan asked for, and close the run through the sim CLI. You do that as a dispatcher over three sequential sub-Tasks, gating each time on what the wave left on disk rather than on what it says about itself.

You never author TB inline, never read the TB body, and never re-run heavy EDA: what you read is status files, envelopes and paths.

Iron Rule

  • Write only under {workdir}. Every injected input location is read-only, as is every other stage's output.
  • Scripts are black boxes, never Read their source. Invoke them per this skill's documented command lines (flags via --help); on a non-zero exit act on the documented failure protocol (stderr, stdout verdict), not the source. Sole exception: debugging a suspected bug in a script itself.
  • The DUT RTL is never the reference. No refmodel, scoreboard or checker may be written from reading RTL source: a golden model taken off the implementation mirrors its bugs and can never disagree with it, so a testbench built that way passes whatever the design does. RTL reaches this stage through the compile filelist and nowhere else.

What you read, and who writes the rest

<skill> is this skill's own base directory, named on the first line of this file.

{workdir}/dispatch.json carries the inputs table below, so <key> denotes a location and you read <key>/<subpath>. None of it needs an existence check: the kernel dispatches you only once each input's producer has recorded it and the fingerprint on disk still matches.

Path Use
<scaffold>/tb-scaffold.json + <scaffold>/sequences.json The plan's judgment: which agent owns which interface_group, and what to run. agents / sequences / tests are what gets materialized into SV; testpoints[] carry the check semantics (inlined_check_hints[]), what each testpoint drives (intent) and what it should reach (bins). top names the DUT. A sub-Task input: you hand over the path.
<plan>/verification-plan.md The human-readable plan the env-build child fills intent against. A sub-Task input; you hand over the path.
<rtl>/rtl-files.json Per-child DUT file layout, which bootstrap turns into rtl_filelist.f. Schema: skills/rtl-design/references/rtl-files.schema.json.
<spec>/top-io.json + <spec>/clocks.json The DUT boundary. bootstrap derives every vif signal, every clock generator and the reset polarity from these at render time — the scaffold does not restate them, so nothing you see in the TB can disagree with what specification declared.

Read the full file on GitHub · 223 lines

Files

What ships with it

49 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.

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. yesterday First seen · 223 lines · 34 tokens per session scan A d660d8cdaae7

Subscribe to this mod's changes

simulation is a skill published in the GitHub repository chipweaver/veripower (4 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 3,138 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 2026-08-31.

PlanningTestingai-agentschip-designclaude-codeclaude-code-pluginrtl-designsystemverilog
Related

Other skills, from other repositories

vdesign

Generate a design proposal, documentation, and RTL backbone from a requirement file.

phamcuong21478/rtl-skills · 17 tokens

varch

Decompose an IP requirement into submodules, define interfaces, and generate an architecture document plus per-module requirement files and a top-level skeleton.

phamcuong21478/rtl-skills · 30 tokens

vfill

Implement Verilog code from an approved design proposal, then lint and simulate.

phamcuong21478/rtl-skills · 17 tokens

vflow

Scan project state to determine phase completion, write flowstatus.md, and orchestrate the full RTL design flow from architecture to documentation.

phamcuong21478/rtl-skills · 28 tokens

vsynth

Synthesize a Verilog module or full IP with Vivado and report resource utilization, Fmax, and power.

phamcuong21478/rtl-skills · 25 tokens

vexplain

Generate documentation for any RTL module from Verilog source files.

phamcuong21478/rtl-skills · 15 tokens