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 simulationgit 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/simulation)<a href="https://agentmods.dev/skills/chipweaver/veripower/simulation"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/simulation/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/simulation"><img src="https://agentmods.dev/badge/skills/chipweaver/veripower/simulation.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 | $0.00029 | $0.01011 |
| Opus 5.5 | $0.00012 | $0.00404 |
| Sonnet 5.5 | $0.00006 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
simulation 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Functional Simulation
Establish whether the implementation meets the applicable behavior and coverage requirements. The stage owner assesses source, reports and review evidence to reach the conclusion. Implement or delegate focused work; use an independent reviewer for check adequacy.
Read {workdir}/dispatch.json for the current inputs and work scope. intent, requirements,
plan, scaffold, check_hints, spec and rtl provide original requirements, verification
strategy, boundary and implementation. Write under {workdir}; upstream artifacts are read-only.
Use the original algorithm/specification as the reference. Inspecting RTL to diagnose a failure
must not turn the implementation into its own expected behavior.
See artifacts.md for report locations and which diagnostic files are published or retained per run.
Build and check
Continue from carried TB and results, changing what the current inputs or failures require. Use env-task-contract.md for setup and materialization details, and authoring-checks.md for check semantics. If delegating, supply the relevant input paths and work scope; collect the actual results before acting on them.
Compile changed sources, run appropriate smoke checks and validate materialization. Missing test results or a failed tool command require investigation; neither identifies the repair owner by itself. Repair local faults and retry affected work. Return an upstream defect with evidence when it cannot be repaired within this stage.
Have the TB reviewed using check-review-task-contract.md. Assess all findings by their evidence and acceptance impact, including those labeled non-blocking. Validate repairs and obtain independent reassessment of changed checks or disputed findings. Retain the review record and report incomplete reviews or unresolved violations at closure.
Verify and diagnose
What ships with it
45 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/artifacts.md 1.4 KB
- references/authoring-checks.md 1.1 KB
- references/check-review-task-contract.md 1.9 KB
- references/coverage-iteration.md 1.2 KB
- references/env-task-contract.md 2.5 KB
- references/result.schema.json 1.5 KB
- references/verify-task-contract.md 1.6 KB
- scripts/sim/__init__.py 0 B runs code
- scripts/sim/__main__.py 4.4 KB runs code
- scripts/sim/bootstrap.py 6.5 KB runs code
- scripts/sim/boundary.py 5.1 KB runs code
- scripts/sim/checks.py 8.7 KB runs code
- scripts/sim/materialization.py 1.1 KB runs code
- scripts/sim/plan.py 402 B runs code
- scripts/sim/rendering.py 1.2 KB runs code
- scripts/sim/result.py 8.0 KB runs code
- scripts/sim/rtl_sources.py 1.7 KB runs code
- scripts/sim/scaffold.py 23 KB runs code
- templates/infra/env.sh 1.0 KB runs code
- templates/infra/Makefile 1.4 KB
- templates/infra/scripts/dump.tcl 889 B
- templates/infra/scripts/parse_coverage.py 11 KB runs code
- templates/infra/scripts/run_vcs_regression.sh 5.7 KB runs code
- templates/infra/scripts/select_tests.py 1.1 KB runs code
- templates/infra/scripts/write_summary.py 5.3 KB runs code
- templates/infra/tb/uvm/seq/base_seq.sv 353 B
- templates/infra/tb/uvm/test/base_test.sv 662 B
- templates/scaffold/agent_agent.sv 1.3 KB
- templates/scaffold/agent_driver.sv 1.2 KB
- templates/scaffold/agent_field_macros.svh 160 B
- templates/scaffold/agent_fields.svh 160 B
- templates/scaffold/agent_if.sv 965 B
- templates/scaffold/agent_monitor.sv 1.4 KB
- templates/scaffold/agent_signals.svh 169 B
- templates/scaffold/agent_txn.sv 759 B
- templates/scaffold/env.sv 1015 B
- templates/scaffold/filelist.f 616 B
- templates/scaffold/reset.svh 180 B
- templates/scaffold/rule_rm.sv 1.7 KB
- templates/scaffold/scoreboard.sv 2.0 KB
- templates/scaffold/seq.sv 895 B
- templates/scaffold/tb_pkg.sv 1.0 KB
- templates/scaffold/tb_sources.f 547 B
- templates/scaffold/tb_top.sv 1.4 KB
- templates/scaffold/test.sv 526 B
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 · -139 lines · -5 tokens per session a89126bc12e0
- 1mo ago Changed · -1 lines 9cde44e341fc
- 1mo ago Changed f1197bd939e4
- 1mo ago Changed · +2 lines 705114a072fa
- 1mo ago First seen · 223 lines · 34 tokens per session scan A d660d8cdaae7
simulation is a skill published in the GitHub repository chipweaver/veripower (10 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,011 once invoked, about $0.0001 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
vtestgen
Scaffold a Makefile-driven, CPU-bus-controlled testbench project for an IP and generate a comprehensive set of self-checking testcases, validate each with make, and write a testcase list.
vtestrun
Run all IP-level testcases from tclist.md through the bench Makefile, capture results, and write per-failure issue reports with no fix suggestions.
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.