simulation-plan

A verification-planning skill creates a written plan and supporting files for checking a hardware module. It covers test points and power-related scenarios, but does not build or run the testbench.

In plain words
What is it for?
It is for planning tests for digital hardware modules, including what to check and which power scenarios to cover.
Why use it?
It turns a module specification into a reviewable checklist, helping teams decide what must be tested before implementation and simulation.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,262 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 $0.00038 $0.02262
Opus 5 $0.00019 $0.01131
Sonnet 5 $0.00008 $0.00452
Haiku 4.5 $0.00004 $0.00226

Measured 2d ago against content hash dba388dfc884, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simulation-plan 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 2d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/simplan/__init__.py, scripts/simplan/__main__.py, scripts/simplan/_plan.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-plan/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Planning

Your sole responsibility: from specification, produce verification-plan.md — the human-readable review anchor — plus its machine half, three sidecars split so each downstream consumer declares only what it reads.

Iron Rule

  • Write only under {workdir}; never another module's artifacts.
  • Do not read RTL source, do not invoke EDA tools. A plan written from the implementation verifies the implementation against itself.

Artifacts

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

Read {workdir}/dispatch.json for this round's inputs: its inputs table maps each upstream key to a location, so <key>/<subpath> is how you address one. design / manifest / children / clocks / features / check_hints / top_io all resolve to the specification stage root.

Path What it is
<design>/design.md §1 behavior, §1.4 boundary, and §1.5 timing scenarios with their waveforms — the only home for the scenarios you author sequences from, so you read it
<children>/<child>.md Per-child implementation constraints a testpoint may have to verify: register side effects, exceptions, concurrency, back-pressure, reset, state-machine boundaries
<design>/features.json The feature list you author testpoints and tests from
<check_hints>/ (per child, one file) Per child, the checks that verify it — check_id is unique across all of them
<design>/clocks.json, <design>/top-io.json The clock and the DUT boundary materialize-scaffold derives from
<manifest>/manifest.json .module is the Top field in plan §1; children[] is the roster the check hints are aggregated over

Everything below is produced under {workdir}.

Path What it is
verification-plan.md The review anchor the human gate is held over (template: references/verification-plan-template.md)
tb-scaffold.json What simulation builds the TB from: agents / tests / testpoints[] / rm / scoreboard / skipped_checks[]
sequences.json The sequence roster — the one part both simulation and power-analysis read
power-scenarios.json The power scenarios, read by power-analysis alone. Its own file so a scenario-only edit does not invalidate simulation's proof
plan-review/review.md, plan-review/decisions.md The reviewer's findings, and the user's resolution of anything it called blocking
result.json The status envelope

Read the full file on GitHub · 163 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. 2d ago First seen · 163 lines · 38 tokens per session scan A dba388dfc884

Subscribe to this mod's changes

simulation-plan is a skill published in the GitHub repository chipweaver/veripower (4 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 2,262 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.