living-codex-browser-builder
Build and evolve an AI-native browser stack (Living Codex Browser / AetherBrowse) using existing SCBE infrastructure. Use when implementing browser architecture, headless research lanes, UI panels, agent routing, or browser reliability/performance upgrades across Electron, Playwright, and runtime APIs.
Best use case
living-codex-browser-builder is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build and evolve an AI-native browser stack (Living Codex Browser / AetherBrowse) using existing SCBE infrastructure. Use when implementing browser architecture, headless research lanes, UI panels, agent routing, or browser reliability/performance upgrades across Electron, Playwright, and runtime APIs.
Teams using living-codex-browser-builder 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/living-codex-browser-builder/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How living-codex-browser-builder Compares
| Feature / Agent | living-codex-browser-builder | 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?
Build and evolve an AI-native browser stack (Living Codex Browser / AetherBrowse) using existing SCBE infrastructure. Use when implementing browser architecture, headless research lanes, UI panels, agent routing, or browser reliability/performance upgrades across Electron, Playwright, and runtime APIs.
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.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Living Codex Browser Builder ## Overview Execute browser development as a lifecycle, not ad hoc patches. Prefer upgrading existing AetherBrowse systems over rebuilding from scratch. ## Default Architecture Use **Infestation mode** by default: - Keep Electron shell as primary product container. - Keep FastAPI runtime as control plane. - Keep Playwright worker as browser execution engine. - Add headless research as a dedicated lane, not mixed with user-facing coding panels. Only switch to alternate architecture if there is a hard blocker: - Hive Mind mode (extension-first): use when shell work is minimal. - Chrysalis mode (web app + browser split): use when strict isolation is required. ## Development Flow Use this exact loop for every browser feature: 1. Plan - Define feature goal, constraints, affected modules, and acceptance tests. 2. Architect - Choose integration points across: - `aetherbrowse/electron/*` - `aetherbrowse/runtime/*` - `aetherbrowse/worker/*` - `src/api/*` when API surface changes are needed. 3. Evaluate - Verify design for: - governance boundaries - headless vs visible path separation - performance and failure blast radius. 4. Implement - Ship smallest useful slice. - Keep patches scoped and reversible. 5. Test - Run module compile/lint/unit/smoke checks. - Run one real navigation task. 6. Fix - Patch only verified failure points. 7. Test - Re-run failed checks and smoke path. 8. Improve - Optimize routing, reliability, or UX after stability. 9. Test - Confirm no regressions after improvements. 10. Fix or Launch - If risk remains: fix and loop. - If green: launch. 11. Launch - Publish release notes with changed files and verification results. ## Browser Lane Rules Use dual browser engines intentionally: - `playwriter`: preferred for signed-in existing-tab flows. - `playwright`: preferred for isolated automation and deterministic headless runs. Always route tasks first: - `python scripts/system/browser_chain_dispatcher.py --domain <domain> --task <task> --engine playwriter|playwright` ## Definition of Done - Feature works end-to-end in one real browser path. - Logs are written to artifact lanes. - Tests/smokes pass. - No unrelated files are touched. - Final output includes what changed, how verified, and next launch action. ## Output Contract Return: - `files_changed` - `verification_run` - `known_risks` - `launch_state` (`hold` or `go`)
Related Skills
scbe-browser-sidepanel-ops
Build, improve, and package the local AetherBrowse browser with an AI sidepanel workflow, governance checks, and app-store-ready Android artifacts.
aetherbrowser-shopify-nav
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
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
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
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
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
Navigate arXiv papers and topic searches through AetherBrowser for research extraction workflows. Use when collecting abstracts, paper metadata, and evidence snapshots from arxiv.org.
scbe-browser-swarm-ops
Coordinate multi-agent browser work with deduplicated task routing, prompt-injection membrane checks, and resilient storage topology. Use when asked to run multi-site research, orchestrate parallel browsing agents, or harden browser automation against malware and injection.
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.