p3-uarch-orchestrator

p3-uarch-orchestrator is an agent for Claude Code from babyworm/rtl-agent-team. It costs 68 tokens per session (6,058 once invoked), scanned A, original, MIT.

A coordinator for designing a chip's microarchitecture, the internal structure and timing of its hardware. It manages parallel microarchitecture and bus-functional-model work, validation, reviews, feedback, and final design documentation.

In plain words
What is it for?
Use it to coordinate microarchitecture design, develop and validate a bus functional model, review convergence, gather design-pattern advice, and finalize clock-domain, protocol, and pipeline documentation.
Why use it?
It helps organize detailed hardware design decisions and check that the planned structure can be exercised and validated. It also records important implementation information before the design moves forward.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool; mentions Codex.

Part of the rtl-agent-team plugin — 47 skills, 99 agents, 6 hooks shipped together

Good fit Use it to coordinate microarchitecture design, develop and validate a bus functional model, review convergence, gather design-pattern advice, and finalize clock-domain, protocol, and pipeline documentation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/babyworm/rtl-agent-team/p3-uarch-orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/babyworm/rtl-agent-team

Made for: Claude Code.

Or install rtl-agent-team, the plugin that ships this one along with the rest of its 47 skills, 99 agents, 6 hooks.

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 p3-uarch-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p3-uarch-orchestrator/github.svg)](https://agentmods.dev/agents/babyworm/rtl-agent-team/p3-uarch-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p3-uarch-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p3-uarch-orchestrator/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 p3-uarch-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/p3-uarch-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/p3-uarch-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,058 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 $0.00068 $0.06058
Opus 5 $0.00034 $0.03029
Sonnet 5 $0.00014 $0.01212
Haiku 4.5 $0.00007 $0.00606

Measured 9d ago against content hash 80b78033807b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

p3-uarch-orchestrator 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 9d 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/p3-uarch-orchestrator.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 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.

You are the Phase 3 μArch Design Orchestrator. You drive the complete microarchitecture design pipeline from architecture blocks to implementable μArch specifications with BFM validation.

Your job is to CONSULT domain experts (domain-consult), DESIGN μArch via uarch-designer, BUILD BFM in parallel via bfm-dev, VALIDATE via BFM simulation, ITERATE 3-round review with 5 reviewers, and PRODUCE finalized μArch artifacts. You do NOT write μArch docs yourself — you orchestrate agents that do.

The rtl-p3-uarch-policy skill (loaded via skills: field) defines all review criteria, document requirements, naming conventions, and checklists. Reference it for pass/fail decisions.

Workflow

Step 0: Context Bootstrap (MANDATORY)

Project root: resolve all project-relative paths (including .rat/...) via the first available of: explicit PROJECT_ROOT=<abs> line in your spawning prompt > project_root field in .rat/state/spawn-context.json (authoritative when present) > $RAT_PROJECT_ROOT env > process CWD (legacy default).

Read the full file on GitHub · 440 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. 9d ago First seen · 440 lines · 68 tokens per session scan A 80b78033807b

Subscribe to this mod's changes

p3-uarch-orchestrator is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 16d ago), licensed MIT. It adds 68 tokens to every session and 6,058 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.

Related

Other agents, from other repositories