env-precheck

env-precheck is a skill for Claude Code, Codex from chipweaver/veripower. It costs 39 tokens per session (1,114 once invoked), scanned A, original, MIT.

An environment pre-check examines whether the machine has the Python packages, hardware-design tools, licenses, and environment paths needed by VeriPower's pipeline.

In plain words
What is it for?
It is for checking whether this machine can run the project's design, simulation, synthesis, timing, lint, and power-analysis stages.
Why use it?
It reveals missing or unusable prerequisites before a pipeline stage is started, reducing failures caused by the machine rather than the design.

Skill for Claude CodeCodex

Part of the veripower plugin — 12 skills, 3 hooks shipped together

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

Made for: Claude Code, Codex.

Or install veripower, the plugin that ships this one along with the rest of its 12 skills, 3 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 env-precheck

README.md
[![agentmods](https://agentmods.dev/badge/skills/chipweaver/veripower/env-precheck.svg)](https://agentmods.dev/skills/chipweaver/veripower/env-precheck)
Your own site
<a href="https://agentmods.dev/skills/chipweaver/veripower/env-precheck"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/env-precheck.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 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 $0.00039 $0.01114
Opus 5 $0.00019 $0.00557
Sonnet 5 $0.00008 $0.00223
Haiku 4.5 $0.00004 $0.00111

Measured 3d ago against content hash f40c5814b365, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

env-precheck 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 3d 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.

skills/env-precheck/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment Pre-check

Pre-pipeline, own session. Write no module file, append no event, call no kernel.py verb. Report only; nothing in the pipeline depends on this having run.

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

1. Presence

<skill>/../../docs/eda-env.md is the requirement source — read it and run each row's sanity check rather than restating it here. Two exceptions: its check for LIB_DB / LIB_V / UVM_HOME is a stage env.sh guard that presupposes a deployed work tree, so here test that each is set and its path readable; and make / urg have no row there at all. timeout every probe — an unreachable license server hangs the tool.

What a missing row costs:

Missing Stages lost
python3, jsonschema >= 4.18, referencing, PyYAML all
/bin/sh → bash, make every EDA stage
vcs, urg, fsdbreport, fsdb2vcd, UVM_HOME simulation, power-analysis, simulation-triage
dc_shell, a DC-Ultra checkout, LIB_DB synthesis, timing-analysis, power-analysis
pt_shell timing-analysis, power-analysis
LIB_V power-analysis
spyglass lint-cdc

specification, simulation-plan and rtl-design need only the first row.

2. Smoke

Presence is not a checkout. Ask which stages to cover — cover every row when there is nobody to ask — then run one minimal job per row in a temp dir: write the DUT (one clocked flop), the TB (import uvm_pkg::*) and each tcl yourself, mirroring how that stage invokes the tool in <skill>/../<stage>/templates/. A row passes iff it produces the file below.

Checkout Hinges on Produces Gates
Design Compiler compile_ultra (the DC-Ultra checkout — the flow runs no plain compile), then write the netlist synthesis
PrimeTime report_timing on that netlist the timing report timing-analysis
PrimeTime-PX set power_enable_analysis TRUE + report_power the power report power-analysis
VCS + UVM compiling uvm_pkg.sv and uvm_dpi.cc from UVM_HOME, then running simv whatever the TB writes simulation, power-analysis
VCS coverage -cm line+cond+branch+tgl+fsm, then urg -report cov_merge -format text cov_merge/dashboard.txt simulation coverage gate
Verdi / FSDB -debug_access+all -kdb -lca + a ucli $fsdbDumpvars, then fsdbreport (argv form in simulation-triage's SKILL.md) the fsdbreport output simulation waveform, simulation-triage
SpyGlass Lint current_goal lint/lint_rtl + run_goal that goal's moresimple.rpt lint-cdc
SpyGlass CDC cdc/cdc_setup, cdc/cdc_setup_check, cdc/cdc_verify_struct, each run_goal each goal's moresimple.rpt lint-cdc

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 39 tokens per session scan A f40c5814b365

Subscribe to this mod's changes

env-precheck is a skill published in the GitHub repository chipweaver/veripower (4 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 1,114 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.