Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/phamcuong21478/rtl-skillsnpx agentmods add skills/phamcuong21478/rtl-skills/vtestrunWrote 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/phamcuong21478/rtl-skills/vtestrun)<a href="https://agentmods.dev/skills/phamcuong21478/rtl-skills/vtestrun"><img src="https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vtestrun/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/phamcuong21478/rtl-skills/vtestrun"><img src="https://agentmods.dev/badge/skills/phamcuong21478/rtl-skills/vtestrun.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 | $0.00035 | $0.01827 |
| Opus 5 | $0.00017 | $0.00914 |
| Sonnet 5 | $0.00007 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade C, and why
vtestrun scanned grade C with 1 finding 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf sim/tb_<module> && make tb_<module> # stale/missing — rebuild fresh How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verilog Testcase Runner
Overview
This skill runs every IP-level testcase listed in tc_list.md through the
Makefile-driven bench that vtestgen scaffolded, captures the build/simulation
logs, and writes a structured issue report for each failure.
The input is an IP name. The outputs are:
./issue/<ip>/issue_NNN_<tcname>.md— one file per failing testcase./issue/<ip>/run_summary.md— overall pass/fail count and failure index
This skill reports failure context only. It does not analyze root cause, propose fixes, or suggest code changes.
Prerequisites
| Tool | Purpose | Check |
|---|---|---|
| xvlog | compile / lint | xvlog --version |
| xelab | elaborate | xelab --version |
| xsim | simulate | xsim --version |
| make | build orchestration | make --version |
Step 1 - Read the testcase list
Read tb/<ip>/tc_list.md and parse the testcase table into a run list. Include only
rows with status OK; skip rows with status SKIPPED.
For each entry record: file (the .sv), module (the tb_* module, equal to the
file base name), category, and description. Confirm tb/<ip>/Makefile and
tb/<ip>/script/rtl.f exist before proceeding.
Step 2 - Create the output directory
Create ./issue/<ip>/ if absent. Do not delete existing issue files; new files use
the next available NNN index (continue from the highest existing index, else start
at 001).
Step 3 - Run each testcase
Run from inside tb/<ip>/. vtestrun is the authoritative pass/fail, but it
does not need to re-simulate testcases that vtestgen already ran — the
verdict is the same [FINISH] token. Re-running everything would just repeat
vtestgen's self-check sims. The one thing it must never do is trust a stale
result (a simulate.log older than an RTL/TB source it depends on — e.g. after a
Phase 6 RTL fix), because the build rule no-ops while a simulate.log exists and
make cleanf keeps prior PASS dirs.
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.
- 11d ago First seen · 180 lines · 35 tokens per session scan C cc0bbec96872
vtestrun is a skill published in the GitHub repository phamcuong21478/rtl-skills (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,827 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
simulation
Use when materializing and running a module's UVM TB from an approved verification plan (regression, coverage); not for plan authoring or RTL changes.
synthesis
Use when running Design Compiler synthesis, analyzing timing/area/power reports, supplementing SDC exceptions, or re-synthesizing after RTL changes; not for power analysis or static timing.
lint-cdc
Use when running SpyGlass lint or CDC checks, analyzing violations, adding waivers, supplementing SGDC annotations, or re-running after RTL changes; not for synthesis or simulation.
power-analysis
Use when running gate-level power simulation + PT-PX averaged power analysis (SAIF flow) for PPA gating; not for RTL functional simulation, static timing, or time-resolved waveforms.
simulation-plan
Use when generating or evolving the verification plan, scaffold specification, testpoints, and power scenarios for a module; not for materializing UVM TB or running EDA tools.
design-flow
Use when progressing IC design through stages, checking module status, or routing rework decisions; not for single-stage execution or artifact authoring.