hydra-node-terminal-browsing
Use when HYDRA tasks need Node.js-first terminal browsing, deterministic page extraction, and evidence JSON output that can be routed into hydra swarm workflows.
Best use case
hydra-node-terminal-browsing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when HYDRA tasks need Node.js-first terminal browsing, deterministic page extraction, and evidence JSON output that can be routed into hydra swarm workflows.
Teams using hydra-node-terminal-browsing 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/hydra-node-terminal-browsing/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How hydra-node-terminal-browsing Compares
| Feature / Agent | hydra-node-terminal-browsing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when HYDRA tasks need Node.js-first terminal browsing, deterministic page extraction, and evidence JSON output that can be routed into hydra swarm workflows.
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
# Hydra Node Terminal Browsing
## Overview
Use this skill for fast terminal-first web/repo browsing in HYDRA workflows when you need deterministic, auditable output instead of conversational browsing.
This skill is optimized for the HYDRA 3-gap surfaces:
- `hydra/browsers.py`
- `hydra/swarm_browser.py`
- `hydra/cli_swarm.py`
## When To Use
Trigger this skill when the user asks to:
- browse websites from terminal with Node.js
- collect page evidence in JSON for later agent decisions
- run HYDRA swarm tasks with explicit browser/LLM backend flags
- produce reproducible extraction artifacts (title, text excerpt, links, status)
Do not use this skill for deep JavaScript rendering correctness testing. For full rendering, use HYDRA Playwright backend directly.
## Quick Start
### 1) Deterministic terminal browse (Node)
```powershell
node C:\Users\issda\.codex\skills\hydra-node-terminal-browsing\scripts\hydra_terminal_browse.mjs --url "https://example.com" --out "artifacts\page_evidence.json"
```
Output is structured JSON with:
- `url`, `resolved_url`, `status`
- `title`
- `text_excerpt`
- `links[]`
- `metrics` and `fetched_at`
### 2) Run HYDRA swarm browser CLI
```powershell
python -m hydra.cli_swarm --status
python -m hydra.cli_swarm --dry-run "research SCBE-AETHERMOORE on GitHub"
python -m hydra.cli_swarm --provider local --backend playwright "navigate to example.com and summarize"
python -m hydra.cli_swarm --provider hf --model mistralai/Mistral-7B-Instruct-v0.3 "find latest PQC migration notes"
```
## Workflow Decision Tree
1. Need simple extraction only:
- Use `hydra_terminal_browse.mjs`.
2. Need multi-agent action execution (navigate/click/type/verify):
- Use `python -m hydra.cli_swarm ...`.
- Start with `--dry-run` before live browser actions.
3. Need repeatable research trail:
- Save extraction JSON with `--out`.
- Keep file path in your task notes for traceability.
## Output Contract (Recommended)
When using terminal browse for governance/evidence tasks, persist output in this shape:
```json
{
"url": "https://...",
"resolved_url": "https://...",
"status": 200,
"title": "...",
"text_excerpt": "...",
"links": ["https://..."],
"metrics": {
"html_chars": 0,
"text_chars": 0,
"link_count": 0,
"truncated": false
},
"fetched_at": "2026-02-22T00:00:00Z"
}
```
## Safety And Quality Gates
- Default to read-only browsing for discovery.
- For HYDRA swarm runs, prefer `--dry-run` first.
- Keep extraction deterministic:
- fixed timeout
- fixed max chars
- deduplicated links
- Never embed secrets/tokens in captured artifacts.
## Resources
### scripts/
- `hydra_terminal_browse.mjs`: Node CLI for deterministic terminal browsing and evidence JSON export.
### references/
- `hydra-browser-surfaces.md`: quick map of HYDRA browser-related modules and test targets.Related Skills
hydra-deep-research-self-healing
Run deep-research loops with HYDRA/Agent Relay using self-healing workflow methods (sense, plan, execute, verify, recover), combining arXiv routing, Playwright evidence capture, synthesis smoke checks, and CI triage hooks. Use when operating long-running 24/7 research automation with deterministic cross-talk logging.
scbe-training-pair-authoring
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
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
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
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
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.
scbe-autonomous-worker-productizer
Turn SCBE automation, autonomous worker, and revenue-system notes into concrete offers, workflow packs, pilot plans, or SaaS-facing product packets. Use when Codex needs to package Notion automation pages into buyer-ready offerings, n8n/Zapier workflow designs, flock-backed worker systems, or implementation roadmaps tied to existing SCBE repo surfaces.
multi-agent-cloud-offload
Deterministically sort, bundle, verify, and offshore local files through multiple AI/model lanes while capturing training rows and method evidence. Use when Codex needs to inventory folders, batch-process files, upload them to cloud targets such as rclone-backed Google Drive, Hugging Face, or GitHub, and only delete sources after the configured number of verified targets succeed.
long-form-work-orchestrator
Run long-form engineering work in checkpointed phases with deterministic artifacts, resilience handling, and end-of-run reliability reporting.
scbe-code-scanning-ops
Operate GitHub code scanning and CodeQL remediation for SCBE repositories. Use when triaging code-scanning alerts, mapping alert classes to fix patterns, validating targeted regressions, or wiring dedicated CodeQL workflows and runbooks into the repo.
cloud-storage-local-storage-management
Audit, sort, route, and back up large Windows workspaces across local disks and cloud-sync folders without recursive mirror failures. Use when the user wants the filesystem cleaned up, cloud storage organized, backup targets chosen by free space and route quality, or hardware/storage bottlenecks identified before moving data.