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/power-analysisnpx skills add chipweaver/veripower --skill power-analysisgit 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/power-analysis)<a href="https://agentmods.dev/skills/chipweaver/veripower/power-analysis"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/power-analysis.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 | $0.00043 | $0.01863 |
| Opus 5 | $0.00022 | $0.00932 |
| Sonnet 5 | $0.00009 | $0.00373 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
power-analysis 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.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Analysis
Your sole responsibility: run VCS gate-level simulation against the post-synthesis netlist and the
UVM TB infrastructure to produce one SAIF per power scenario, run PrimeTime PX in averaged mode
over each of them, and close the run through the power CLI. You never grade power_mw by eye —
finalize parses the reports, judges the target, and writes the verdict.
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.
What you read, and what you produce
<skill> is this skill's own base directory, named on the first line of this file.
{workdir}/dispatch.json carries the inputs table, and you open almost none of what it points
at: bootstrap resolves <TOP> from the single out/<TOP>_syn.v under the synthesis stage root
and writes every upstream location into env.sh, which the make targets read from there. The
netlist, the SDC and the SDF are consumed by the tools; VCS back-annotates delays out of the SDF,
which is what makes the SAIF a gate-level one rather than an RTL toggle count.
The one file you open yourself is <ppa>/ppa.json, and only when a power_mw miss makes you
decide which side of it is wrong. finalize reads it for the gate on its own.
Three env vars are yours to supply before make:
LIB_V |
std-cell Verilog models, linked against the netlist at compile time |
LIB_DB |
the Liberty .db synthesis linked against — PT maps activity to power through it, so a different library is a different answer |
UVM_HOME |
the UVM tree the TB infrastructure was built against |
env.sh refuses to run unless all three name readable files, and every target sources it, so a
wrong path stops the run at the first target instead of after the simulation.
What ships with it
15 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.
- references/result.schema.json 7.7 KB
- scripts/power/__init__.py 0 B runs code
- scripts/power/__main__.py 3.8 KB runs code
- scripts/power/bootstrap.py 7.4 KB runs code
- scripts/power/result.py 21 KB runs code
- templates/env.sh 3.1 KB runs code
- templates/Makefile 4.8 KB
- templates/README.md 1012 B
- templates/scaffold/power_test.sv.tmpl 1.9 KB
- templates/scripts/build_tb_filelist_abs.py 2.6 KB runs code
- templates/scripts/check_sdf_annotated.sh 1.8 KB runs code
- templates/scripts/emit_power_tests.py 6.1 KB runs code
- templates/scripts/extract_power_scenarios.py 767 B runs code
- templates/scripts/ptpx.tcl 9.0 KB
- templates/scripts/run_gls_power.sh 3.9 KB runs code
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.
- 4d ago First seen · 132 lines · 43 tokens per session scan A 9ec323f2b682
power-analysis is a skill published in the GitHub repository chipweaver/veripower (4 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,863 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.