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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chipweaver/veripower/power-analysis"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/power-analysis.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.01273 |
| Opus 5.5 | $0.00017 | $0.00509 |
| Sonnet 5.5 | $0.00008 | $0.00255 |
| Haiku 4.5 | $0.00004 | $0.00127 |
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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power Analysis
Establish the intended operating conditions, capture their activity, calculate power, and explain what the measurement establishes. The supplied tools use gate-level simulation, SAIF and PT-PX interval-average power; this does not establish instantaneous peak power or IR drop.
Read {workdir}/dispatch.json for input locations. intent, design and requirements give the
goals, design choices and budgets. Read both plan/verification-plan.md for measurement meaning
and plan/power-scenarios.json for identifiers. netlist/out/ contains the implementation and
constraints; tb_env provides reusable verification sources, data, scripts and setup. Inspect what
you reuse, including any services behind a reference-model bridge. Write under {workdir};
shared inputs remain read-only.
Choose the work from the evidence
The framework carries published experiment sources, setup and measurements into {workdir},
without the old verdict. Choose the work from changed inputs and the measurement being claimed.
Reuse artifacts whose implementation, conditions and scope still apply; a budget-only change can use existing reports.
For a new workdir, prepare editable setup (<skill> is this skill's directory):
python3 <skill>/scripts/power/__main__.py bootstrap --workdir {workdir} [--top <TOP>]
Bootstrap resolves the netlist top and plan, and installs missing templates. It does not run tools or require simulation inputs for a calculation-only task. Existing authored files survive rework; check their settings against this round's inputs. Use the project's actual libraries and models.
From {workdir}, source env.sh and select the needed command:
. ./env.sh
python3 <skill>/scripts/power/__main__.py COMMAND --workdir .
| COMMAND | Work performed |
|---|---|
compile |
Build the authored experiment and check SDF annotation |
simulate |
Run planned scenarios using the existing executable |
calculate |
Read checked activity and calculate power in a fresh PT process per scenario |
What ships with it
11 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 6.8 KB
- scripts/power/__init__.py 0 B runs code
- scripts/power/__main__.py 3.4 KB runs code
- scripts/power/bootstrap.py 1.9 KB runs code
- scripts/power/execute.py 4.3 KB runs code
- scripts/power/requirements.py 3.0 KB runs code
- scripts/power/result.py 20 KB runs code
- scripts/power/scenarios.py 899 B runs code
- templates/env.sh 416 B runs code
- templates/scripts/check_sdf_annotated.sh 2.0 KB runs code
- templates/scripts/ptpx.tcl 1.8 KB
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.
- 1mo ago Changed · -32 lines · -1 tokens per session c8764837e333
- 1mo ago Changed 210c46ce5f84
- 1mo ago Changed · +6 lines acdb553494a0
- 1mo ago First seen · 132 lines · 43 tokens per session scan A 9ec323f2b682
power-analysis is a skill published in the GitHub repository chipweaver/veripower (10 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 1,273 once invoked, about $0.0002 per session on Opus 5.5. 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.