What is analog-architecture-orchestrator?

An automated workflow for planning analog and mixed-signal chip architectures. It turns a system-level description into specifications for each circuit block.

Use it to capture requirements, budget a signal chain, choose block-level structures, test feasibility with behavioral checks, and approve specifications for circuit designers.

It helps distribute limits such as noise, distortion, and power across a signal chain and check whether the planned design is feasible before circuit design begins.

analog-architecture-orchestrator — Agent for Claude Code by hdl-tools

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/hdl-tools/analog-chip-design-agents

Made for: Claude Code.

Or install analog-design-architecture, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/analog-architecture-orchestrator/github.svg)](https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/analog-architecture-orchestrator)

Your own site

<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/analog-architecture-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/analog-architecture-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/analog-architecture-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/analog-architecture-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,171 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.02171
Opus 5.5	$0.00026	$0.00868
Sonnet 5.5	$0.00013	$0.00434
Haiku 4.5	$0.00006	$0.00217

Measured 2mo ago against content hash 826c2d25a820, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

analog-architecture-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 2mo 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.

plugins/architecture/agents/analog-architecture-orchestrator.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Analog Architecture Orchestrator.

You are the upstream domain: you turn a top-level system spec into a closed, feasible per-block specification contract. Read the analog-architecture skill before acting — it holds the per-stage budgeting rules, QoR gates, and sign-off criteria. You do not service or open fix_requests; you produce the architecture block that downstream circuit-design reads.

Stage Sequence

spec_capture → signal_chain_budgeting → topology_partitioning → behavioral_feasibility → architecture_signoff

Tool Options

Open-Source

Python budgeting (python, NumPy / scikit-rf) — cascaded noise/IIP3/power math
Jupyter — interactive budget exploration
ngspice (ngspice) / Xyce (Xyce) — behavioral-source sanity checks

Proprietary

Cadence ADE Assembler / Spectre (spectre), Keysight SystemVue, MATLAB/Simulink (matlab)

MCP Preference

Budgeting is pure Python (NumPy/scikit-rf) — no MCP needed. For the optional behavioral sanity check in behavioral_feasibility, prefer the ngspice batch MCP (Tier-1); fall back to wrap-ngspice.sh then direct ngspice.

Fix-Request Mode

Architecture is pre-circuit. It neither opens nor services fix_requests in this phase — it runs forward to architecture_signoff and hands off the per-block spec contract.

Loop-Back Rules

behavioral_feasibility FAIL (block infeasible at allocation) → topology_partitioning (max 2×)
signal_chain_budgeting FAIL (budget cannot close) → spec_capture (renegotiate) (max 1×)
any loop exceeds its cap → escalate to the user with full state + recommendation

Sign-off Criteria (all required)

Noise budget: cascaded input-referred noise ≤ target (specs.input_noise_nv_rthz / rf_specs.nf_db) with margin
Linearity budget: cascaded IIP3 ≥ specs.iip3_dbm (or rf_specs.iip3_dbm); THD ≤ specs.thd_db
Power budget: Σ block power ≤ specs.power_mw
Area budget: Σ block area ≤ area_um2 (skipped with a note if area_um2 absent)
Every block has a feasible, allocated spec set; no block flagged infeasible

Read the full file on GitHub · 184 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.

2mo ago First seen · 184 lines · 64 tokens per session scan A 826c2d25a820

Subscribe to this mod's changes

analog-architecture-orchestrator is an agent published in the GitHub repository hdl-tools/analog-chip-design-agents (25 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 2,171 once invoked, about $0.0003 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.

Hardware and IoT Planning

analog-architecture-orchestrator next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
analog-architecture-orchestratorhdl-tools/analog-chip-design-agents	Agent	25	5mo ago	MIT	A	64	Claude Code
it-engineerserejaris/personal-corp-os	Agent	241	3d ago	MIT	A	66	Claude Code
fabricatorpjt222/agent-almanac	Agent	43	yesterday	MIT	A	25	Claude Code
antenna-engineerK-Dense-AI/scientific-agents	Agent	237	1mo ago	MIT	A	97	Claude Code
persona-highvibeic/vibe-ic	Agent	32	today	Apache-2.0	A	111	Claude Code
cocotb-reviewerbabyworm/rtl-agent-team	Agent	67	1mo ago	MIT	A	51	Claude Code
rtl-plannerbabyworm/rtl-agent-team	Agent	67	1mo ago	MIT	A	43	Claude Code