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.
npx agentmods add skills/chipweaver/veripower/env-prechecknpx skills add chipweaver/veripower --skill env-precheckgit clone --depth 1 https://github.com/chipweaver/veripowerWrote 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.
[](https://agentmods.dev/skills/chipweaver/veripower/env-precheck)<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 3d ago First seen · 69 lines · 39 tokens per session scan A f40c5814b365
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.
Other skills, from other repositories
vdesign
Generate a design proposal, documentation, and RTL backbone from a requirement file.
varch
Decompose an IP requirement into submodules, define interfaces, and generate an architecture document plus per-module requirement files and a top-level skeleton.
vfill
Implement Verilog code from an approved design proposal, then lint and simulate.
vflow
Scan project state to determine phase completion, write flowstatus.md, and orchestrate the full RTL design flow from architecture to documentation.
vsynth
Synthesize a Verilog module or full IP with Vivado and report resource utilization, Fmax, and power.
vexplain
Generate documentation for any RTL module from Verilog source files.