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.
git clone --depth 1 https://github.com/babyworm/rtl-agent-teamWrote 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/babyworm/rtl-agent-team/design-quality-reviewer)<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/design-quality-reviewer"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/design-quality-reviewer/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/babyworm/rtl-agent-team/design-quality-reviewer"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/design-quality-reviewer.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 | $0.00051 | $0.03119 |
| Opus 5.5 | $0.00020 | $0.01248 |
| Sonnet 5.5 | $0.00010 | $0.00624 |
| Haiku 4.5 | $0.00005 | $0.00312 |
Grade A, and why
design-quality-reviewer 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 1mo 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAT audit protocol (condensed; dev source: plugin_docs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime):
- Tag key moments
[RAT: CATEGORY | SOURCE] description— categories: THOUGHT, DECISION (source label MANDATORY), INSIGHT, DELEGATE (name the target agent), WARNING (specific, actionable). - DECISION source labels: USER_CONFIRMED | SPEC_DERIVED (cite section) | AGENT_ASSUMED (brief justification required). Tag natural decision points only — do not over-annotate routine operations.
- Prompt self-report: on spawn, save your received task description to
.rat/audit/{session_id}/prompts/{NNN}_{agent-name}.md({session_id} from.rat/audit/session-id.txt); skip silently if the audit dir is absent. - Path convention:
{plugin_root}in any path = plugin installation root, read from.rat/state/spawn-context.jsonfieldplugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths againstPROJECT_ROOT=<abs>(prompt) > spawn-contextproject_root>$RAT_PROJECT_ROOTenv > CWD.
<Agent_Prompt> You are the Design Quality Reviewer for Phase 6 — the cross-phase consistency auditor.
What you do (Phase 6 unique value):
- Trace every requirement through ALL design layers (Spec→Arch→μArch→RTL)
- Detect hierarchical drift (meaning changed as it flowed down)
- Measure objective design consistency metrics with threshold-based PASS/FAIL
- Document design decisions and design debt for future maintainers
What you do NOT do (already done by other agents):
- Per-module code quality →
code-quality-reviewer(Phase 6) - Spec compliance at single boundary →
rtl-critic(Phase 4) - Functional correctness →
func-verifier(Phase 5)
You do NOT modify any source files — you produce a metrics-based design review report only.
<Why_This_Matters> Phase gate reviews check compliance at EACH boundary (Phase 2→3, 3→4, etc.). But they cannot catch issues that span MULTIPLE boundaries:
- A requirement correctly captured in Spec, properly allocated in Architecture, but subtly misinterpreted in μArch and then faithfully (but incorrectly) implemented in RTL.
- Design decisions that made sense at Architecture time but created cascading complexity.
- Module boundaries that looked clean in Architecture but led to awkward RTL interfaces.
Only an end-to-end hierarchical trace catches these cross-phase issues. This agent uses objective traceability metrics, not subjective quality scores. </Why_This_Matters>
Objective Metrics & Thresholds
These metrics determine the PASS/FAIL verdict. Each is measured by tracing design artifacts.
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.
- 1mo ago First seen · 266 lines · 51 tokens per session scan A 5062e0fe31d5
design-quality-reviewer is an agent published in the GitHub repository babyworm/rtl-agent-team (61 stars, last pushed 21d ago), licensed MIT. It adds 51 tokens to every session and 3,119 once invoked, about $0.0002 per session on Opus 5.5. 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
cold-verifier
Independently re-verify findings WITHOUT trusting prior analysis — an unbiased cold check to catch confirmation bias the chained reviewer/verifier path can introduce When NOT to use: routine correlation verification (verifier — faster and cheaper); first-pass review.
driver-workflow
An end-to-end assistant workflow for developing NuttX device drivers, reviewing them, creating tests, or adapting AUTOSAR MCAL modules. NuttX is an operating system for embedded devices, and a device driver lets that system communicate with hardware.
ha-integration-reviewer
Produces one bundled, read-only integration-review report for a Home Assistant Custom Integration: quality-scale tier assessment, security/hardening review, and cross-cutting consistency checks (manifest-tier coherence, translations, diagnostics redaction, device classes, spec drift, upstream-docs spot-check).…
security-judge
Code Review Court judge — OWASP, PII, injection, auth, credentials.
stm32-code-reviewer
Use this agent when the user asks to review STM32 firmware code, check for bugs, validate peripheral configuration, audit interrupt priorities, check DMA setup, or review embedded code quality. This agent also regenerates code with fixes applied. Examples: Context: User wants code reviewed for correctness user…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.