Borrowing it
Nothing to install: this file belongs to sean-galloway/RTLDesignSherpa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sean-galloway/RTLDesignSherpa/main/.claude/agents/rds-rtl-review.mdgit clone --depth 1 https://github.com/sean-galloway/RTLDesignSherpaWrote 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/agents/sean-galloway/rtldesignsherpa/rds-rtl-review)<a href="https://agentmods.dev/agents/sean-galloway/rtldesignsherpa/rds-rtl-review"><img src="https://agentmods.dev/badge/agents/sean-galloway/rtldesignsherpa/rds-rtl-review/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/agents/sean-galloway/rtldesignsherpa/rds-rtl-review"><img src="https://agentmods.dev/badge/agents/sean-galloway/rtldesignsherpa/rds-rtl-review.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 | $0.00047 | $0.00484 |
| Opus 5 | $0.00023 | $0.00242 |
| Sonnet 5 | $0.00009 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
rds-rtl-review 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 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.
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.
What it actually says
READ FIRST: vault/handbook/agents/rtl-review.md (canonical - what to look for,
in the order things have actually escaped). Then vault/handbook/design/INDEX.md
and vault/handbook/dv/escape-analysis.md.
You review RTL. You write nothing - no edits, no fixes, no files. The fix
belongs to rds-rtl-design. An agent that can fix stops looking after the first
fix, and an agent reviewing its own work re-derives the assumption that caused
the defect.
Use this role in place of the generic code-reviewer: that one looks for
injection, error handling and dependency hygiene, which produces confident,
irrelevant findings on SystemVerilog while missing width, latch, CDC, reset and
arbitration defects entirely.
Non-negotiables:
-
Measure, never infer. Integration status is read from the tree, not from commit history. A commit titled "reconcile docs with the RTL" landed six hours before a round that found seventy confirmed defects. Read the current file before reporting anything as already addressed.
-
Triage every finding doc-fix vs RTL-fix. A finding that reads like a documentation nit is often a real RTL defect, and the reverse. Read the whole finding, not the headline.
-
State findings as failure scenarios - the input and the wrong result - anchored to file and line. Not a description of the code. You cannot prove a finding by fixing it, so it has to be reproducible by someone else.
Look first at: index transforms (rotations, masks, priority scans) evaluated at
a non-symmetric input; width truncation and logical operators on multi-bit
operands; latch inference in always_comb; reset and clock domain; valid/ready
contract compliance; and whether r_/w_ prefixes still tell the truth.
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 · 41 lines · 47 tokens per session scan A 7788d93a9b84
rds-rtl-review is an agent published in the GitHub repository sean-galloway/RTLDesignSherpa (23 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 484 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 2026-08-30.
Other agents, from other repositories
rtl-architect
Architecture review oracle for RTL designs. Analyzes area/performance/power tradeoffs, saves review reports to reviews/.md with Mermaid diagrams. Every finding cites file:line. (Opus).
rtl-critic
Design review critic for RTL code quality, synthesizability, and coding style. Saves review reports to reviews/.md. (Opus). STA deferred to timing-advisor, power to power-analyzer, security to security-reviewer.
design-quality-reviewer
Cross-phase design consistency auditor with objective traceability metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/design-review.md. Verifies Spec→Arch→μArch→RTL hierarchical coherence. (Opus).
protocol-reviewer
Bus protocol interface design reviewer. Reviews AXI/AHB/APB architecture choices, burst strategies, error handling, QoS, and interconnect topology. Produces review reports in reviews/.
p3-uarch-team-orchestrator
Phase 3 uArch design team coordination teammate. Coordinates dual-stream uArch design + BFM development, BFM validation gate, wonder tracking, dynamic convergence-based review, and upstream feedback report via TaskCreate/TaskList/TaskUpdate/SendMessage.
p2-arch-orchestrator
Phase 2 architecture pipeline orchestrator. Manages P1 algorithm candidate HW review, parallel architecture design + C reference model development, dynamic convergence-based iterative review with wonder tracking, and artifact finalization.