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 simra-tech/OpenADA --skill review-rtl-architecturegit clone --depth 1 https://github.com/simra-tech/OpenADAWrote 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/simra-tech/openada/review-rtl-architecture)<a href="https://agentmods.dev/skills/simra-tech/openada/review-rtl-architecture"><img src="https://agentmods.dev/badge/skills/simra-tech/openada/review-rtl-architecture.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 131 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00084 | $0.02488 |
| Opus 5 | $0.00042 | $0.01244 |
| Sonnet 5 | $0.00017 | $0.00498 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
review-rtl-architecture 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 8d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review RTL Architecture
Review the implemented RTL as a senior design reviewer, but keep every
conclusion inside the available evidence. Use $openada:openada for execution
and normalized results. Never teach this workflow a native tool command, parse
a native log into a second result, or rename a missing check as passed.
Define the decision
State the application, design phase, top module, and immediate decision. Ask whether the review is intended to establish:
- the declared source configuration and successful elaboration;
- strict diagnostic cleanliness;
- a plausible architecture for the declared throughput, latency, area, power, clock, reset, and test goals; or
- readiness for a separate synthesis, timing, CDC/RDC, formal, simulation, or implementation workflow.
These are different claims. RTL lint does not prove function, CDC safety, reset release safety, timing, power, equivalence, or specification satisfaction.
Freeze the source configuration
Record one review manifest before invoking an operation:
- repository revision and exact ordered source files;
- top module, SystemVerilog revision, include directories, defines, and generated-source identity;
- declared clocks, clock relationships, reset domains and polarities, intended operating modes, and interface protocols;
- authoritative architecture/specification references and unresolved assumptions;
- selected operation/feature, implementation, native product/version, evidence directory, result-envelope path, artifact paths, byte counts, and hashes.
The current result envelope has no general request or result correlation field; do not invent one. Bind reviews with the repository revision, exact file and artifact hashes, operation profile, tool identity, and evidence path instead.
Do not guess the top, file order, defines, clock intent, reset intent, or a black-box model. The v1alpha1 lint surface has no module-parameter override; if the intended configuration requires one, report that configuration as not evaluated instead of silently using defaults. If any supported choice can change elaboration, stop and ask one narrow question. Treat source and PDK/library trees as read-only and use a fresh task-local evidence directory.
What ships with it
1 file 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.
- 8d ago First seen · 248 lines · 84 tokens per session scan A 68bae96faab7
review-rtl-architecture is a skill published in the GitHub repository simra-tech/OpenADA (25 stars, last pushed 26d ago), licensed MIT. It adds 84 tokens to every session and 2,488 once invoked, about $0.0004 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.
Other skills, from other repositories
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
cdc-tool-profiles
Internal reference: cdc tool profiles (agent-loaded; do not invoke).
refactor-classification-policy
Internal reference: refactor classification policy (agent-loaded; do not invoke).
code-review-policy
Internal reference: code review policy (agent-loaded; do not invoke).
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.