aetherbrowse-ops

Use when starting, stopping, monitoring, or managing the AetherBrowse browser stack. Triggers on "start aetherbrowse", "launch browser", "aetherbrowse health", "browser profiles", "governance logs", "hydra armor usage", "aetherbrowse status", or "runtime health".

6 stars

Best use case

aetherbrowse-ops is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when starting, stopping, monitoring, or managing the AetherBrowse browser stack. Triggers on "start aetherbrowse", "launch browser", "aetherbrowse health", "browser profiles", "governance logs", "hydra armor usage", "aetherbrowse status", or "runtime health".

Teams using aetherbrowse-ops should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/aetherbrowse-ops/SKILL.md --create-dirs "https://raw.githubusercontent.com/issdandavis/SCBE-AETHERMOORE/main/.agents/plugins/plugins/aetherbrowse/skills/aetherbrowse-ops/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/aetherbrowse-ops/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How aetherbrowse-ops Compares

Feature / Agentaetherbrowse-opsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when starting, stopping, monitoring, or managing the AetherBrowse browser stack. Triggers on "start aetherbrowse", "launch browser", "aetherbrowse health", "browser profiles", "governance logs", "hydra armor usage", "aetherbrowse status", or "runtime health".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# AetherBrowse Operations Guide

Operate the AetherBrowse governed AI browser stack.

## Stack Components

The full AetherBrowse stack has 3 processes:

| Process | Command | Port | Required |
|---------|---------|------|----------|
| Agent runtime | `python aetherbrowse/runtime/server.py` | 8400 | Yes |
| Playwright worker | `python aetherbrowse/worker/browser_worker.py` | connects to 8400 | For automation |
| Electron shell | `cd aetherbrowse && npm run dev` | connects to 8400 | For GUI |

## Starting the Stack

### Minimal (runtime only)

```bash
cd C:\Users\issda\SCBE-AETHERMOORE
python -m uvicorn aetherbrowse.runtime.server:app --host 127.0.0.1 --port 8400
```

### Runtime + Worker

```bash
# Terminal 1: Runtime
python -m uvicorn aetherbrowse.runtime.server:app --host 127.0.0.1 --port 8400

# Terminal 2: Worker
python aetherbrowse/worker/browser_worker.py
```

### Full stack with Electron

```bash
# Terminal 1: Runtime
python -m uvicorn aetherbrowse.runtime.server:app --host 127.0.0.1 --port 8400

# Terminal 2: Worker
python aetherbrowse/worker/browser_worker.py

# Terminal 3: Electron
cd aetherbrowse && npm run dev
```

## Health Checks

### Runtime health
```bash
curl http://127.0.0.1:8400/health
```
Returns: `{"status": "ok", "electron": bool, "worker": bool, "agents": {...}}`

### Full system status
```bash
curl http://127.0.0.1:8400/api/status
```
Returns runtime connection state, current URL, action count, and agent statuses.

### Hydra Armor health
```bash
curl http://127.0.0.1:8400/v1/armor/health
```
Returns OctoArmor and SCBE governance availability.

### Agent usage stats
```bash
curl http://127.0.0.1:8400/v1/armor/usage/{agent_id}
```

## Browser Profiles

Persistent browser profiles with storage state live at:
```
aetherbrowse/profiles/<profile_id>/storage_state.json
```

### Commands via runtime
- `switch profile to <profile_id>` — switch active browser profile
- `list profiles` — show available profiles
- `autofill login for <domain> [submit]` — autofill saved credentials

### Import Google passwords
```powershell
python scripts/system/import_google_password_export.py `
  --csv "C:\path\to\Google Passwords.csv" `
  --profile-id creator-main
```

## Governance Logs

| Log File | Content |
|----------|---------|
| `artifacts/aetherbrowse/governance.jsonl` | All governance decisions |
| `artifacts/aetherbrowse/actions.jsonl` | Browser actions taken |
| `artifacts/agent_comm/aetherbrowse/runs.jsonl` | Plan execution runs |
| `artifacts/agent_comm/aetherbrowse/search_queries.jsonl` | Search query history |
| `artifacts/aetherbrowse/hydra_usage.jsonl` | Hydra Armor API usage |
| `artifacts/aetherbrowse/cost_log.jsonl` | LLM cost tracking |
| `training-data/aetherbrowse/governance_pairs.jsonl` | SFT training pairs |

### View recent runs
```bash
curl http://127.0.0.1:8400/api/runs/latest?limit=5
```

### View specific run
```bash
curl http://127.0.0.1:8400/api/runs/{run_id}
```

## Search Engine Configuration

Multi-engine search with roundtable, DuckDuckGo, Bing, and fallback routing. Test via:
```bash
curl "http://127.0.0.1:8400/api/search?q=test+query&limit=5"
```

## Model Routing

LLM provider configuration lives in `aetherbrowse/config/model_routing.yaml`:
- `governance_check` → free tier (Groq/Cerebras)
- `page_understanding` → cheap tier (Gemini Flash)
- `action_planning` → cheap tier (Gemini/OpenRouter)
- `complex_reasoning` → premium tier (Claude/Grok)

Daily budget: `$1.00` (configurable in `cost_tracking.daily_budget_usd`).

## Electron Desktop Build

```bash
cd aetherbrowse
npm run build:win    # Windows (NSIS + portable + zip)
npm run build:dir    # Directory output only
```

Output: `artifacts/releases/aetherbrowse-desktop/`

## Troubleshooting

- **Runtime won't start**: Check `fastapi` and `uvicorn` are installed: `pip install fastapi uvicorn websockets`
- **Worker can't connect**: Ensure runtime is running first, worker connects to `ws://127.0.0.1:8400/ws/worker`
- **Electron shows blank**: Runtime must be running before Electron launches
- **No search results**: Check DuckDuckGo rate limiting; fallback URLs will be returned
- **Governance DENY on everything**: Check `governance_policies.yaml` domain lists and coherence thresholds

Related Skills

aetherbrowser-shopify-nav

6
from issdandavis/SCBE-AETHERMOORE

Navigate Shopify admin and storefront pages through AetherBrowser for merchandising and operations tasks. Use when working on products, collections, orders, settings, or marketing surfaces in browser mode.

aetherbrowser-operator

6
from issdandavis/SCBE-AETHERMOORE

Operate AetherBrowser as the primary online task surface across search, GitHub, Codespaces, research, Notion, Hugging Face, Shopify, and general web work. Use when Codex should drive a real browser session first, coordinate with built-in search or fetch tools second, capture page-state proof, and keep online work inside the SCBE browser lane instead of defaulting to generic web automation.

aetherbrowser-notion-nav

6
from issdandavis/SCBE-AETHERMOORE

Navigate Notion workspace pages in AetherBrowser for knowledge retrieval and workspace coordination tasks. Use when locating pages, databases, or section paths in browser mode before API operations.

aetherbrowser-huggingface-nav

6
from issdandavis/SCBE-AETHERMOORE

Navigate Hugging Face models, datasets, and spaces through AetherBrowser for research, validation, and publishing workflows. Use when inspecting repo cards, files, docs, and leaderboard surfaces in browser mode.

aetherbrowser-github-nav

6
from issdandavis/SCBE-AETHERMOORE

Navigate GitHub repositories, pull requests, issues, and settings through AetherBrowser tentacle routing. Use when tasks require browser-based GitHub movement, page evidence capture, or coordinated lane assignment with playwriter or playwright.

aetherbrowser-arxiv-nav

6
from issdandavis/SCBE-AETHERMOORE

Navigate arXiv papers and topic searches through AetherBrowser for research extraction workflows. Use when collecting abstracts, paper metadata, and evidence snapshots from arxiv.org.

aetherbrowse-dev

6
from issdandavis/SCBE-AETHERMOORE

Use when developing, extending, or debugging the AetherBrowse governed AI browser. Triggers on mentions of "aetherbrowse", "agent runtime", "perceiver", "planner", "browser worker", "hydra armor", "hydra bridge", "governance policy", "model routing", "octoarmor", or "aether://".

scbe-training-pair-authoring

6
from issdandavis/SCBE-AETHERMOORE

Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.

scbe-spin-conversation-engine

6
from issdandavis/SCBE-AETHERMOORE

Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.

scbe-research-training-bridge

6
from issdandavis/SCBE-AETHERMOORE

Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.

scbe-document-management

6
from issdandavis/SCBE-AETHERMOORE

Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.

scbe-colab-bridge

6
from issdandavis/SCBE-AETHERMOORE

Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.