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 ArabelaTso/Skills-4-SE --skill rtl-equivalence-checkergit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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/arabelatso/skills-4-se/rtl-equivalence-checker)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/rtl-equivalence-checker"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/rtl-equivalence-checker/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/arabelatso/skills-4-se/rtl-equivalence-checker"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/rtl-equivalence-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.02068 |
| Opus 5.5 | $0.00050 | $0.00827 |
| Sonnet 5.5 | $0.00025 | $0.00414 |
| Haiku 4.5 | $0.00013 | $0.00207 |
Grade A, and why
rtl-equivalence-checker 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 2mo 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RTL Equivalence Checker
Verify functional equivalence between two RTL designs with detailed analysis and counterexample generation.
Overview
This skill compares two Verilog RTL designs to determine if they are functionally equivalent. It aligns interfaces and state variables, distinguishes semantic differences from cosmetic refactoring, and generates minimal counterexample traces when designs differ.
Workflow
1. Basic Equivalence Check
Compare two RTL designs:
python3 scripts/check_equivalence.py design_a.v design_b.v
Output includes:
- Equivalence verdict (EQUIVALENT or NOT EQUIVALENT)
- Explanation of differences
- Counterexample trace (if not equivalent)
2. With Assumptions
Specify clock and reset behavior:
python3 scripts/check_equivalence.py design_a.v design_b.v \
--clock clk \
--reset rst_n \
--reset-active low
3. Save Results
Write results to file:
python3 scripts/check_equivalence.py design_a.v design_b.v -o results.txt
4. Ignore Signal Names
Focus on functional behavior, ignore naming differences:
python3 scripts/check_equivalence.py design_a.v design_b.v --ignore-names
Analysis Process
The checker performs five steps:
[1/5] Parsing RTL designs
- Extracts module structure
- Identifies ports, signals, and state elements
- Parses always blocks and assignments
[2/5] Aligning interfaces and state variables
- Matches ports by name and type
- Aligns state elements (registers)
- Reports unmatched signals
[3/5] Analyzing behavioral differences
- Identifies cosmetic differences (naming, formatting)
- Identifies semantic differences (logic changes)
- Categorizes difference types
[4/5] Determining equivalence
- Verdict: EQUIVALENT or NOT EQUIVALENT
- Based on semantic differences only
- Cosmetic differences don't affect equivalence
[5/5] Generating counterexample (if not equivalent)
- Creates minimal test sequence
- Shows input values that expose difference
- Traces outputs from both designs
What ships with it
6 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.
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.
- 2mo ago First seen · 332 lines · 126 tokens per session scan A b1cae492ae66
rtl-equivalence-checker is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (260 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 126 tokens to every session and 2,068 once invoked, about $0.0005 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 2026-09-03.
rtl-equivalence-checker compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rtl-equivalence-checkerArabelaTso/Skills-4-SE | Skill | 260 | 2mo ago | Apache-2.0 | A | 126 | Claude Code, Codex |
| skill-code-qualitysaitarrun/Sdlc-ai-workflow | Skill | 6 | 1mo ago | none | A | 34 | Claude Code |
| diagnosesaitarrun/Sdlc-ai-workflow | Skill | 6 | 1mo ago | none | A | 66 | Claude Code |
| skill-pr-reviewsaitarrun/Sdlc-ai-workflow | Skill | 6 | 1mo ago | none | A | 65 | Claude Code |
| teachsaitarrun/Sdlc-ai-workflow | Skill | 6 | 1mo ago | none | A | 15 | Claude Code |
| improve-codebase-architecturesaitarrun/Sdlc-ai-workflow | Skill | 6 | 1mo ago | none | A | 68 | Claude Code |
| skill-developer-relationssaitarrun/Sdlc-ai-workflow | Skill | 6 | 1mo ago | none | A | 46 | Claude Code |