pyslang-verilog-context

pyslang-verilog-context is a skill for Codex from ariklapid/pyslang-mcp. It costs 107 tokens per session (1,093 once invoked), scanned A, original, Apache-2.0.

A coding guide for using pyslang-mcp, a read-only compiler-based analyzer for Verilog and SystemVerilog hardware code.

In plain words
What is it for?
Use it for syntax and semantic diagnostics, file lists, modules, interfaces, packages, ports, hierarchy, symbols, includes, defines, reviews, debugging, and refactoring.
Why use it?
It helps an agent understand the correct files, dependencies, definitions, and hardware structure before answering questions or changing RTL code.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it for syntax and semantic diagnostics, file lists, modules, interfaces, packages, ports, hierarchy, symbols, includes, defines, reviews, debugging, and refactoring.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ariklapid/pyslang-mcp/pyslang-verilog-context
Install

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.

Any agent
npx skills add ariklapid/pyslang-mcp --skill pyslang-verilog-context
Clone the repo
git clone --depth 1 https://github.com/ariklapid/pyslang-mcp

Made for: Codex.

Wrote 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.

agentmods badge for pyslang-verilog-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/ariklapid/pyslang-mcp/pyslang-verilog-context/github.svg)](https://agentmods.dev/skills/ariklapid/pyslang-mcp/pyslang-verilog-context)
Your own site
<a href="https://agentmods.dev/skills/ariklapid/pyslang-mcp/pyslang-verilog-context"><img src="https://agentmods.dev/badge/skills/ariklapid/pyslang-mcp/pyslang-verilog-context/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.

agentmods 80×15 button for pyslang-verilog-context

Your own site · 80×15
<a href="https://agentmods.dev/skills/ariklapid/pyslang-mcp/pyslang-verilog-context"><img src="https://agentmods.dev/badge/skills/ariklapid/pyslang-mcp/pyslang-verilog-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.01093
Opus 5 $0.00053 $0.00547
Sonnet 5 $0.00021 $0.00219
Haiku 4.5 $0.00011 $0.00109

Measured 12d ago against content hash 4d8a6911a31f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pyslang-verilog-context 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 12d 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.

skills/pyslang-verilog-context/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pyslang-verilog-context

Use pyslang-mcp as read-only compiler-backed context for Verilog and SystemVerilog work. Keep normal file editing outside the MCP tools.

First Decision

Use pyslang-mcp when the answer depends on any of these:

  • parse or semantic diagnostics
  • filelist expansion, include dirs, or defines
  • module, interface, or package inventory
  • ports, declarations, child instances, or hierarchy
  • declaration/reference lookup
  • syntax-shape or preprocessing metadata
  • RTL edits that should preserve an existing compile context

Use direct file reads and rg first for tiny lexical questions, comments, renames, or incomplete snippets where a compiler frontend cannot add much.

Workflow

  1. Establish the HDL input boundary.

    • Prefer user-provided project_root, files, filelist, include dirs, defines, and top modules.
    • Otherwise infer the smallest conservative project root that contains the source set.
    • Keep all paths under project_root.
  2. Load the project.

    • Use pyslang_parse_filelist for .f inputs.
    • Use pyslang_parse_files for explicit .sv, .svh, .v, or .vh inputs.
    • Pass known include_dirs, defines, and top_modules; do not invent them when the repo does not provide them.
  3. Check diagnostics early.

    • Call pyslang_get_diagnostics before making structural claims.
    • Treat parse or semantic errors as primary evidence and explain how they limit downstream analysis.
    • Do not claim the RTL is functionally correct because diagnostics are clean.
  4. Ask focused follow-up questions.

    • Use pyslang_list_design_units to discover modules, interfaces, and packages.
    • Use pyslang_describe_design_unit for ports, declarations, and child instances.
    • Use pyslang_get_hierarchy for instance tree questions.
    • Use pyslang_find_symbol for declarations and references.
    • Use pyslang_summarize_diagnostics_by_code before scanning long raw diagnostics in large RTL projects.
    • Use pyslang_find_member when the question is local to one design unit and pyslang_find_symbol is too broad.
    • Use pyslang_get_assignments for "what drives this signal" or "where is this signal used on the RHS" questions.
    • Use pyslang_get_instance_connections when one instance's port bindings are needed without a full hierarchy dump.
    • Use pyslang_trace_connectivity for bounded structural tracing through assignments and instance port bindings.
    • Use pyslang_preprocess_files for include/define questions.
    • Use pyslang_dump_syntax_tree_summary for syntax-shape questions.
    • Use pyslang_get_project_summary when a compact overview is enough.

Read the full file on GitHub · 114 lines

Files

What ships with it

60 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.

Changes

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.

  1. 12d ago First seen · 114 lines · 107 tokens per session scan A 4d8a6911a31f

Subscribe to this mod's changes

pyslang-verilog-context is a skill published in the GitHub repository ariklapid/pyslang-mcp (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,093 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

cardputer-buddy

Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…

anthropics/claude-plugins-official · 109 tokens

doca-argp

Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…

NVIDIA/skills · 267 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens

zener-language

Read or edit Zener HDL, package APIs, and tool-managed dependencies.

diodeinc/pcb · 19 tokens

embedded-stm32

Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…

Mindrally/skills · 87 tokens

001-commands-inventory

Use when you need to generate a checklist document with embedded commands inventory, following the embedded template exactly and producing INVENTORY-COMMANDS-JAVA.md in the project root. This should trigger for requests such as Create embedded commands inventory checklist; Generate INVENTORY-COMMANDS-JAVA.md; Use…

jabrena/plinth · 92 tokens