RTLDesignSherpa: Agent for Claude Code

.claude/agents/rds-regress.md

rds-regress is an agent for Claude Code from sean-galloway/RTLDesignSherpa. It costs 48 tokens per session (413 once invoked), scanned A, original, MIT.

An agent for running hardware regressions and classifying their failures. A regression is a repeated test run used to find whether changes broke existing behavior.

In plain words
What is it for?
Running clean regression builds, recording failing seeds, triaging failures, deciding when to quarantine tests, and routing findings to the right hardware or verification agent.
Why use it?
It separates hardware defects, test defects, flaky results, and infrastructure problems before anyone attempts a fix.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is sean-galloway/RTLDesignSherpa's own configuration. It tells Claude Code how to work on RTLDesignSherpa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RTLDesignSherpa configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/sean-galloway/RTLDesignSherpa/main/.claude/agents/rds-regress.md
Clone the repo
git clone --depth 1 https://github.com/sean-galloway/RTLDesignSherpa

Made for: Claude Code.

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 rds-regress

README.md
[![agentmods](https://agentmods.dev/badge/agents/sean-galloway/rtldesignsherpa/rds-regress/github.svg)](https://agentmods.dev/agents/sean-galloway/rtldesignsherpa/rds-regress)
Your own site
<a href="https://agentmods.dev/agents/sean-galloway/rtldesignsherpa/rds-regress"><img src="https://agentmods.dev/badge/agents/sean-galloway/rtldesignsherpa/rds-regress/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 rds-regress

Your own site · 80×15
<a href="https://agentmods.dev/agents/sean-galloway/rtldesignsherpa/rds-regress"><img src="https://agentmods.dev/badge/agents/sean-galloway/rtldesignsherpa/rds-regress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 413 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 $0.00048 $0.00413
Opus 5 $0.00024 $0.00206
Sonnet 5 $0.00010 $0.00083
Haiku 4.5 $0.00005 $0.00041

Measured 11d ago against content hash 24c0c590ab7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rds-regress 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.

.claude/agents/rds-regress.md · 35 lines

What it actually says

READ FIRST: vault/handbook/agents/regress-triage.md (canonical). Then vault/handbook/dv/running-regressions.md and seeds-and-determinism.md.

You run regressions and decide what kind of failure each one is. You route; you do not repair. An agent that can fix will fix the first failure and stop, and a suite failure is usually a distribution rather than an incident.

Non-negotiables:

  • Clean rebuild before any verdict. A stale sim_build passes against the old RTL and has produced a false all-clear here. Every time, not just when it seems to matter.

  • Never re-run until a seed passes. That converts a real finding into noise. Record the failing seed and hand it on.

  • A quarantine without a recorded reason is a silently deleted test. Every quarantine gets a reason and a task in /vault/Tasks/<area>/open.md.

  • "Fixed" is a measurement. Before reporting anything fixed: a clean rebuild that reproduces the pass, and a mutation check showing the test can still go RED.

Triage categories and where each goes: RTL defect -> rds-rtl-review first (read-only and cheap), then rds-rtl-design. Test defect -> rds-dv. Flake -> quarantine with seed and reason. Infrastructure -> often an unregistered module in bin/filelists.toml, one of the two silent filelist failures.

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. 11d ago First seen · 35 lines · 48 tokens per session scan A 24c0c590ab7f

Subscribe to this mod's changes

rds-regress is an agent published in the GitHub repository sean-galloway/RTLDesignSherpa (23 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 413 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.

Related

Other agents, from other repositories

equivalence-checker

Equivalence checking specialist. Verifies RTL-vs-netlist and RTL-vs-RTL functional equivalence after synthesis, optimization, or ECO changes. Supports Formality (fmshell), Conformal LEC (lec), and Yosys (open-source fallback).

babyworm/rtl-agent-team · 58 tokens

p5s-uvm-orchestrator

UVM verification orchestrator. Manages commercial simulator check (hard gate), test plan generation (ECP/BVA), UVM environment generation, quality review (uvm-reviewer gate), compilation, regression, and structured 3-round CDV feedback loop with coverage-analyst, test-plan-writer, and exclusion protocol.

babyworm/rtl-agent-team · 76 tokens

ppa-optimizer-dc-orchestrator

Coordinator for one PPA optimization iteration. Sequences DC synthesis, report parsing, RTL patching, equivalence, smoke regression, delta computation, and convergence verdict. Self-contained; spawned by rtl-ppa-optimize-dc or rat-ultraloop-ppa skill.

babyworm/rtl-agent-team · 64 tokens

requirement-tracer

Requirement traceability specialist. Maps every spec requirement (REQ-XXXX) to test cases, tracks feature verification status, and identifies untested requirements. Produces traceability matrix reports in reviews/.

babyworm/rtl-agent-team · 43 tokens

testbench-dev

SV testbench and cocotb testbench developer. Designs coverage models, stimulus generators, and covergroups. Ensures functional coverage closure.

babyworm/rtl-agent-team · 32 tokens

formal-reviewer

Formal verification quality reviewer. Reviews SVA assertion completeness, vacuity, assume/assert/cover balance, proof strategy, and SymbiYosys configuration. Produces review reports in reviews/.

babyworm/rtl-agent-team · 42 tokens