Skip to content
Agentmart
Submit a tool

dsg-hybrid-agent

DSG Hybrid Agent - Multi-agent workflow executor with ROM DOM simulation + real browser fallback for DSG Control Plane

Skill by tdealer01-crypto

IndexedMIT★ 12
Write a review

Chalk Labs

Need help deploying dsg-hybrid-agent?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tdealer01-crypto-dsg-hybrid-agent

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

DSG Hybrid Agent - Multi-agent workflow executor with ROM DOM simulation + real browser fallback for DSG Control Plane

Use cases: productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/dsg-hybrid-agent

What's inside

Skill name
dsg-hybrid-agent
Description
DSG Hybrid Agent - Multi-agent workflow executor with ROM DOM simulation + real browser fallback for DSG Control Plane
License
MIT
Instructions
240 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Instructions call the network

Files (9)

  • README.md
  • SKILL.md
  • install.sh
  • README.md · references/
  • recording-guide.md · references/
  • README.md · templates/
  • multi-agent-template.md · templates/
  • task-template.md · templates/
  • task-template.yaml · templates/

SKILL.md (first lines)

# DSG Hybrid Agent Skill

## Overview

This skill provides a **multi-agent workflow executor** for DSG Control Plane that combines:
- **ROM DOM Simulation** (fast, free, deterministic) - runs on Vercel
- **Real Browser Execution** (Browserbase/Stagehand) - for auth/gate eval
- **Verification Gates** (T4 deterministic merge) - ensures sim ≡ real

## Architecture

```
┌─────────────────────────────────────────────────────────────────┐
│                    HYBRID AGENT WORKFLOW                        │
├─────────────────────────────────────────────────────────────────┤
│  Task YAML → PARSE → SIM SESSION → REAL BROWSER (if needed)    │
│       │           │           │              │                  │
│       ▼           ▼           ▼              ▼                  │
│   [Goal]    [Steps]    [Engine]         [Stagehand]             │
│                              │              │                  │
│                              └──────┬───────┘                  │
│                                     ▼                          │
│                            [VERIFICATION GATE T4]             │
│                                     │                          │
│                                     ▼                          │
│                              [MERGED RESULT]                   │
└─────────────────────────────────────────────────────────────────┘
```

## Key Components

### 1. ROM DOM Registry (`src/rom-dom/`)
Pre-recorded DOM snapshots for all DSG pages:
- **Public**: landing, delivery-proof, readiness-report, health, mcp-manifest, compliance-annex4, ccvs-status
- **Protected**: login, hermes-dashboard, gate-evaluate

Each ROM contains:
- Selectors (semantic → CSS)
- Forms (fields, validation, submit)
- Actions (click, type, extract, wait, api-call)
- Simulation rules (input → predicted output)
- Browser actions (Playwright commands)

### 2. Simulation Engine (`src/lib/simulation/engine.ts`)
Pure TypeScript, runs on Vercel:
- `ROMSimulationEngine` - per-ROM simulation
- `SimulationSession` - multi-step workflow with context
- `SimulationEngineFactory` - create engines

### 3. Hybrid API (`app/api/agent/hybrid/route.ts`)
Three modes:
- `sim-only` - Fast, free, no real browser
- `hybrid` - Simulate first, real for auth steps, verify at T4
- `real-only` - Full real browser (slow, costs)

### 4. Task Definitions (`tasks/`)
YAML workflows:
- `login-and-gate-eval.yaml` - Full login + gate evaluation
- `public-recon.yaml` - Public endpoint reconnaissance
- `delivery-proof-scan.yaml` - Delivery proof scanning
- `readiness-check.yaml` - Production readiness
- `ci-cd-pipeline.yaml` - Full CI/CD verification

## Quick Start

### 1. Run Public Recon (SIM ONLY - Free, Instant)
```bash
curl -X POST https://your-app.vercel.app/api/agent/hybrid \
  -H "Content-Type: application/json" \
  -d '{"goal": "Public recon", "mode": "sim-only", "steps": [
    {"type": "api-call", "rom": "health"},
    {"type": "api-call", "rom": "mcp-manifest"},
    {"type": "api-call", "rom": "compliance-annex4"}
  ]}'
```

### 2. Run Full Login + Gate Eval (HYBRID)
```bash
curl -X POST https://your-app.vercel.app/api/agent/hybrid \
  -H "Content-Type: application/json" \
  -d @tasks/login-and-gate-eval.yaml
```

### 3. Use from Hermes Agent
```typescript
// In Hermes agent context
const result = await fetch('https://tdealer01-crypto-dsg-control-plane.vercel.app/api/agent/hybrid', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    goal: 'Login and evaluate gate',
    mode: 'hybrid',
    steps: [...]
  })
});
```

## Multi-Agent Parallel Execution

This skill supports **parallel agent execution** for independent workflows:

```yaml
# Parallel task group
agentGroup:
  - agent: recon-agent
    task: public-recon.yaml
  - agent: compliance-agent
    task: compliance-check.yaml
  - agent: readiness-agent
    task: readiness-check.yaml
```

Each agent runs in isolation with its own `SimulationSession`, then results are merged at T4 gate.

## Verification Gates (T4 Deterministic Merge)

Every hybrid step supports verification:
```yaml
verification:

From tdealer01-crypto/tdealer01-crypto-dsg-control-plane, MIT.

More from tdealer01-crypto/tdealer01-crypto-dsg-control-plane

Signals

Stars
12
Forks
1
Open issues
20
Last commit (this folder)
Jul 31, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tdealer01-crypto

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get dsg-hybrid-agent running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying dsg-hybrid-agent?

CallGet help
Cite this page

dsg-hybrid-agent skill. Agent Mart. https://agentmart.dev/skills/tdealer01-crypto-dsg-hybrid-agent (last updated 2026-10-24)