dse-orchestrator

dse-orchestrator is an agent for Claude Code from babyworm/rtl-agent-team. It costs 56 tokens per session (4,892 once invoked), scanned C, original, MIT.

A coordinator for exploring hardware design options before writing RTL, the code that describes a digital circuit. It leads algorithm study, architecture comparisons, microarchitecture and bus-functional-model work, self-review, and user feedback across several phases.

In plain words
What is it for?
Use it to study algorithms, develop architecture candidates, define the microarchitecture, create a bus functional model for exercising interfaces, run critique cycles, and prepare design artifacts before RTL implementation.
Why use it?
It helps turn an initial hardware idea into a reviewed pre-implementation package. Comparing options before implementation can expose design issues while changes are still easier to make.

Agent for Claude Code

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

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

Good fit Use it to study algorithms, develop architecture candidates, define the microarchitecture, create a bus functional model for exercising interfaces, run critique cycles, and prepare design artifacts before RTL implementation.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/dse-orchestrator.svg)](https://agentmods.dev/agents/babyworm/rtl-agent-team/dse-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/babyworm/rtl-agent-team/dse-orchestrator"><img src="https://agentmods.dev/badge/agents/babyworm/rtl-agent-team/dse-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,892 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00056 $0.04892
Opus 5 $0.00028 $0.02446
Sonnet 5 $0.00011 $0.00978
Haiku 4.5 $0.00006 $0.00489

Measured 8d ago against content hash 10733924a9ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

dse-orchestrator scanned grade C with 1 finding 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Clean up scratch: `rm -rf .rat/scratch/phase-2/`
agents/dse-orchestrator.md · 419 lines

How it starts

The opening of the file, as written. The whole thing — 419 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 DSE Orchestrator. You perform deep, iterative Design Space Exploration through Phase 1 (Research + Algorithm Exploration), Phase 2 (Architecture DSE + Reference C Model), and Phase 3 (μArch + SystemC/C BFM), producing a complete pre-implementation package.

Your job is to EXPLORE alternatives, PRESENT trade-off matrices to the user for decision, DELEGATE detailed work to specialist agents, SELF-CRITIQUE results, RE-RUN the pipeline with critique incorporated, and ENFORCE quality gates. You do NOT write C models, BFMs, or specs yourself — you orchestrate agents that do.

Key principle: Phase 3 produces C/SystemC BFM (executable μArch model), NOT SystemVerilog RTL. DPI bridge templates are prepared for future Phase 4 RTL comparison, but no RTL is written here.

The rat-dse-policy skill (loaded via skills: field) defines the comparison matrix format, candidate evaluation criteria, C model transformation rules, self-critique protocol, trial comparison method, and gate criteria.

Workflow

Read the full file on GitHub · 419 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. 8d ago First seen · 419 lines · 56 tokens per session scan C 10733924a9ab

Subscribe to this mod's changes

dse-orchestrator is an agent published in the GitHub repository babyworm/rtl-agent-team (51 stars, last pushed 15d ago), licensed MIT. It adds 56 tokens to every session and 4,892 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.