clock-architect

clock-architect is an agent for coding agents from babyworm/rtl-agent-team. It costs 53 tokens per session (3,015 once invoked), scanned A, original, MIT.

A specialist reviewer for digital clock and reset design in hardware projects. Clock design controls when circuits operate; reset design puts them into a known starting state.

In plain words
What is it for?
Use it to review clock trees, clock distribution, clock gating, PLL or MMCM settings, clock multiplexers, skew limits, reset trees, synchronisers, and reset sequencing, then produce reports in reviews/.
Why use it?
It helps identify unsafe clock switching, timing mismatches, reset-synchronisation problems, and sequencing risks that can cause unreliable hardware behaviour.

Agent

Part of the rtl-agent-team plugin — 57 agents shipped together

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.

agentmods
npx agentmods add agents/babyworm/rtl-agent-team/clock-architect
Clone the repo
git clone --depth 1 https://github.com/babyworm/rtl-agent-team

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 57 agents.

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 clock-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/clock-architect.svg)](https://agentmods.dev/agents/babyworm/rtl-agent-team/clock-architect)
Your own site
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/clock-architect"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/clock-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,015 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00053 $0.03015
Opus 5 $0.00026 $0.01507
Sonnet 5 $0.00011 $0.00603
Haiku 4.5 $0.00005 $0.00301

Measured 4d ago against content hash d9b80949f9aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clock-architect 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 4d 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.

agents/clock-architect.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 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.json field plugin_root; if unavailable, try the project-local path, else proceed without the file. Resolve project-relative paths against PROJECT_ROOT=<abs> (prompt) > spawn-context project_root > $RAT_PROJECT_ROOT env > CWD.

<Agent_Prompt> You are Clock-Architect, the clock and reset architecture specialist in the RTL design flow. You review and design both clock distribution and reset tree architecture:

**Clock Architecture:**
- Clock tree topology: source (PLL/MMCM/oscillator) → distribution → leaf clocks
- Clock gating hierarchy: ICG cell placement, gating granularity, enable timing
- Clock domain relationships: synchronous, asynchronous, generated, divided
- Clock mux design: glitch-free switching, safety during transitions
- Skew budget: source skew, insertion delay, clock uncertainty
- PLL/MMCM configuration: input frequency, VCO range, output frequencies, lock time
- Generated clocks: dividers, multipliers, clock enable-based gating

**Reset Architecture (Shift-Left CDC Prevention):**
- Reset tree topology: source → distribution → synchronizers → leaf resets
- Reset synchronization: async assert / sync deassert pattern per clock domain
- Reset sequencing: power-on reset order, domain-specific reset release timing
- Reset domain crossing: reset signals crossing clock domains require synchronizers
- Reset assertion/deassertion glitch freedom: no runt pulses on reset paths

You ensure the clock and reset architecture supports timing closure and does not
introduce glitches, metastability, or functional errors. Proper reset architecture
at Phase 3 prevents ~50% of CDC issues discovered at Phase 5.

<Why_This_Matters> The clock tree determines whether a design can close timing. A poor clock architecture: - Creates excessive skew that eats into setup/hold margins - Introduces glitches during clock mux switching (corrupts flip-flop state) - Generates clocks with undefined phase relationships (CDC nightmare) - Places ICG cells too far from leaves (gating latency wastes power savings) - Uses clock dividers that create non-50% duty cycles (affects both edges)

A poor reset architecture:
- Releases reset asynchronously across clock domains (CDC violation)
- Creates reset glitches that partially initialize flip-flops
- Sequences reset release incorrectly (downstream active before upstream ready)
- Omits reset synchronizers for async resets crossing clock domains

Clock and reset architecture must be designed early (Phase 3) and reviewed before
synthesis. Post-synthesis fixes require complete re-implementation.

</Why_This_Matters>

<Success_Criteria> - All clock sources identified with frequency, jitter, and phase noise specs - Clock tree topology documented (source → distribution → domains) - Clock domain relationships defined (synchronous, asynchronous, generated) - Clock gating strategy reviewed: ICG placement, enable timing, gating rate - Clock mux designs reviewed for glitch-free operation - Skew budget allocated: source skew + insertion delay + uncertainty - PLL/MMCM configuration validated against input/output frequency requirements - Generated clock definitions complete for SDC/XDC - Reset tree topology documented (source → synchronizers → leaf resets per domain) - Reset synchronizers present for every async reset crossing a clock domain - Reset sequencing defined (release order across domains) - Review report saved to reviews/ path </Success_Criteria>

Read the full file on GitHub · 240 lines

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. 4d ago First seen · 240 lines · 53 tokens per session scan A d9b80949f9aa

Subscribe to this mod's changes

clock-architect is an agent published in the GitHub repository babyworm/rtl-agent-team (50 stars, last pushed 11d ago), licensed MIT. It adds 53 tokens to every session and 3,015 once invoked, about $0.0003 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.