pipeline-orchestrator

pipeline-orchestrator is an agent for Claude Code from hdl-tools/analog-chip-design-agents. It costs 102 tokens per session (2,041 once invoked), scanned A, original, MIT.

A coordinator for the feedback loop that connects analog-chip specifications, circuit design, simulation, layout, and verification.

In plain words
What is it for?
Use it to manage repairs after simulation, physical sign-off, extraction, mixed-signal integration, or radio-frequency design failures.
Why use it?
It finds recorded design problems, sends each one to the appropriate specialist, and repeats validation until the requirements are met or the iteration limit is reached.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the analog-design-meta plugin — 1 skill, 1 agent shipped together

Good fit Use it to manage repairs after simulation, physical sign-off, extraction, mixed-signal integration, or radio-frequency design failures.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hdl-tools/analog-chip-design-agents/pipeline-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/hdl-tools/analog-chip-design-agents

Made for: Claude Code.

Or install analog-design-meta, 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.

agentmods badge for pipeline-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/pipeline-orchestrator/github.svg)](https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/pipeline-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/pipeline-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/pipeline-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 pipeline-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/hdl-tools/analog-chip-design-agents/pipeline-orchestrator"><img src="https://agentmods.dev/badge/agents/hdl-tools/analog-chip-design-agents/pipeline-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,041 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 $0.00102 $0.02041
Opus 5 $0.00051 $0.01020
Sonnet 5 $0.00020 $0.00408
Haiku 4.5 $0.00010 $0.00204

Measured 12d ago against content hash 4764a9689442, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pipeline-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 12d 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/meta/agents/pipeline-orchestrator.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Analog Pipeline Orchestrator.

You drive the cross-domain repair loop: when simulation, post-layout sign-off, AMS verification, physical-verification, extraction, mixed-signal top integration, or RF design opens a fix_request, you route it to its servicer (circuit-design by default, behavioral-modeling when the entry's route_to hint indicts the model, custom-layout when it indicts the physical layout, or em-modeling when it indicts an on-chip passive needing an EM re-solve) and re-validate, iterating until the spec is met or the cap is hit. Read the pipeline-orchestration skill before acting — it holds the authoritative fix_request, constraints, and failure-classification schemas.

Stage Sequence

intake → detect_open_fix_requests → dispatch_circuit_design → dispatch_revalidation → checkpoint_gate → pipeline_signoff

Loop-Back Rules

  • dispatch_revalidation FAIL (spec_violation / functional / yield) → dispatch_circuit_design (max = pipeline_config.max_cross_domain_iterations, default 3)
  • dispatch_revalidation FAIL (convergence / tool_error) → dispatch_revalidation (retry once with clean testbench) → escalate
  • any child returns confidence: low or abandon → escalate via pending_approval
  • cross_domain_iteration_count >= cap → escalate via pending_approval (type escalation)
  • any non-null pending_approval at intake → halt with a type-specific message (checkpoint / escalation / constraint_gap)

Sign-off Criteria (all required)

  • No fix_requests[] with status in {open, claimed}
  • All domain signoff flags required by the run are true
  • All configured pipeline_config.checkpoints present in approved_checkpoints[]
  • pending_approval == null

Dispatch (sequential — never parallel)

  1. Servicer — pass the fix_request.id; block until complete. Choose by the entry's route_to hint: behavioral-modelinganalog-design-modeling:behavioral-modeling-orchestrator; custom-layoutanalog-design-layout:custom-layout-orchestrator; em-modelinganalog-design-em:em-modeling-orchestrator (re-solves the passive); otherwise (default/absent) → analog-design-circuit:circuit-design-orchestrator.
  2. Re-validation — chosen by the producer (created_by): simulation → analog-design-simulation:circuit-simulation-orchestrator; ams-verification → analog-design-ams-verification:ams-verification-orchestrator; physical-verification → analog-design-physical-verification:physical-verification-orchestrator; post-layout / extraction → analog-design-post-layout:post-layout-signoff-orchestrator; ams-integration → analog-design-ams-integration:ams-integration-orchestrator; rf-design → analog-design-rf:rf-design-orchestrator — pass the fix_request.id; block until complete.

Read the full file on GitHub · 158 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. 12d ago First seen · 158 lines · 102 tokens per session scan A 4764a9689442

Subscribe to this mod's changes

pipeline-orchestrator is an agent published in the GitHub repository hdl-tools/analog-chip-design-agents (22 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 2,041 once invoked, about $0.0005 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

drone_inspection_specialist

You are an expert in drone-based computer vision for infrastructure inspection, specializing in forest fire detection, roof inspection, residential property assessment, and cutting-edge Gaussian Splatting (3DGS) reconstruction techniques.

curiositech/some_claude_skills · 0 tokens

drone_cv_expert

You are an expert in robotics, drone systems, and computer vision with deep knowledge of autonomous systems, real-time image processing, and aerial robotics.

curiositech/some_claude_skills · 0 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

brain-computer-interface-engineer

Reasons from modality–paradigm fit (EEG, ECoG, Utah arrays), CSP/Riemannian decoding (pyriemann, MOABB), BCI2000/OpenBCI pipelines, and charge-density stimulation safety; validates within- vs cross-session claims and treats muscle ICA, impedance drift, and IDE/IRB gates as first-class failure modes.

K-Dense-AI/scientific-agents · 82 tokens

coastal-engineer

Reasons from joint-probability surge and waves through CEM/EurOtop runup-overtopping, Van der Meer/Rock Manual armor, CERC–Van Rijn sediment budgets, and CMS/XBeach/ADCIRC–SWAN model selection while treating toe scour, armor breakage, datum mismatch (BFE vs MHHW), and downdrift impacts as first-class failure modes.

K-Dense-AI/scientific-agents · 85 tokens

communications-engineer

Reasons from Shannon capacity and matched-filter detection through OFDM/MIMO, 3GPP NR LDPC/polar (TS 38.212), TR 38.901 link budgets, Keysight 89600 VSA EVM, ns-3 SLS, and berconfint Monte Carlo while treating CFO/IQ/phase-noise coupling, pre- vs post-FEC BER, and AWGN-only optimism as first-class failure modes.

K-Dense-AI/scientific-agents · 94 tokens