rtl-lint-check

rtl-lint-check is a skill for Claude Code from babyworm/rtl-agent-team. It costs 39 tokens per session (2,043 once invoked), scanned A, original, MIT.

A report-only check for RTL, the code that describes digital hardware, using several lint tools. Lint finds likely design, synthesis, and style problems without running a full verification suite.

In plain words
What is it for?
It helps perform quick sanity checks before commits, generate review reports, and gate hardware design phases.
Why use it?
It catches issues such as width mismatches, unintended latches, driver conflicts, and formatting violations early. The check reports problems but does not fix them.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md.

Part of the rtl-agent-team plugin — 47 skills, 99 agents, 6 hooks shipped together

Good fit It helps perform quick sanity checks before commits, generate review reports, and gate hardware design phases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/babyworm/rtl-agent-team/rtl-lint-check
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 babyworm/rtl-agent-team --skill rtl-lint-check
Clone the repo
git clone --depth 1 https://github.com/babyworm/rtl-agent-team

Made for: Claude Code.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

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 rtl-lint-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-lint-check/github.svg)](https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-lint-check)
Your own site
<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-lint-check"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-lint-check/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 rtl-lint-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/babyworm/rtl-agent-team/rtl-lint-check"><img src="https://agentmods.dev/badge/skills/babyworm/rtl-agent-team/rtl-lint-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,043 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00039 $0.02043
Opus 5 $0.00019 $0.01022
Sonnet 5 $0.00008 $0.00409
Haiku 4.5 $0.00004 $0.00204

Measured 7d ago against content hash b6d010c6c9d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rtl-lint-check 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_conventions.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/rtl-lint-check/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RTL files (rtl/) are linted with slang -Weverything for maximum strictness — this catches IEEE 1800 §9.2.2.4 violations (e.g., always_ff + initial on same signal) that only VCS enforces at compile time. TB files (sim/) use --allow-dup-initial-drivers for flexibility.

Report all violations with file, line, rule, and severity. See references/verilator-warnings.md for detailed Verilator warning categories and waiver format.

<Use_When>

  • Verifying lint status of any RTL file before commit or phase gate
  • Quick sanity check during development
  • Generating lint report for review </Use_When>

<Do_Not_Use_When>

  • Lint fixing is also needed (use rtl-p4-implement or rtl-p4s-refactor which include fix cycles)
  • Full verification suite needed (use rtl-p5s-func-verify or rtl-p4s-unit-test) </Do_Not_Use_When>

<Why_This_Exists> Three complementary lint tools catch different issue classes:

  • Verilator is the most widely-used open-source linter; it catches synthesizability issues (latches, blocking/non-blocking mix, width mismatches) that style linters miss entirely.
  • Verible catches style and formatting issues; slang catches IEEE 1800 semantic issues. Running all three gives comprehensive coverage: synthesizability + style + semantics. </Why_This_Exists>

<Coding_Convention_Requirements> Lint checks MUST enforce the project coding conventions (CLAUDE.md):

  • Port prefix: i_ (input), o_ (output), io_ (bidirectional) — NOT suffix _i, _o
  • Clock: clk (single domain) or {domain}_clk (multiple domains, e.g., sys_clk) — NOT clk_i
  • Reset: rst_n (single domain) or {domain}_rst_n (multiple domains, e.g., sys_rst_n) — NOT rst_ni
  • logic only — reg/wire usage flagged as violation
  • Declaration order (IEEE 1800 §12.5): all logic/typedef/localparam must appear before assign/always blocks — forward references flagged as violation
  • Instance prefix: u_ — missing prefix flagged
  • Generate prefix: gen_ — missing prefix flagged Note: Verible and slang may not catch all convention violations natively. lint-checker MUST perform a supplementary grep-based check for naming conventions. </Coding_Convention_Requirements>

<Execution_Policy>

  • lint-checker runs all three tools in parallel on the target file(s) via Bash CLI
  • Prefer replayable wrapper: lint/scripts/run_lint.sh (creates lint/lint/replay/run_lint_*_latest.sh)
  • Additionally checks naming conventions not caught by standard tools
  • Results merged and de-duplicated
  • Zero-error gate: skill reports PASS or FAIL with full violation list </Execution_Policy>

Read the full file on GitHub · 145 lines

Files

What ships with it

5 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. 7d ago First seen · 145 lines · 39 tokens per session scan A b6d010c6c9d8

Subscribe to this mod's changes

rtl-lint-check is a skill published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 17d ago), licensed MIT. It adds 39 tokens to every session and 2,043 once invoked, about $0.0002 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 2026-09-03.