Recursive web crawling with depth control, pagination detection, and sitemap discovery. Use for comprehensive site coverage when you need to follow links across multiple levels.
Fetch a single web page using Obscura headless browser. Best for public, read-only pages. Returns HTML, plain text, links, or JS-evaluated results.
Multi-step web data collection pipeline using Obscura. Combines fetch + scrape for discover-then-collect workflows. Use when you need to crawl a site systematically.
Scrape multiple URLs in parallel using Obscura. Use when you have a list of URLs to process in batch. Returns JSON or text per URL.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skill-driven plugin for Obscura headless browser — gives AI coding agents direct access to web scraping and browser automation via slash commands.
Two approaches in Obscura:
obscura-plugin(this plugin) — skill-driven with read-only commands (obscura_fetch,obscura_scrape, etc.), designed for autonomous agent pipelines
obscura-plugin ships a .claude-plugin/ manifest. Register the marketplace source once, then install:
claude plugin marketplace add epicsagas/plugins
claude plugin install obscura-plugin
The SessionStart hook downloads obscura and obscura-worker automatically on first load. No manual steps needed.
codex plugin marketplace add epicsagas/plugins
codex plugin install obscura-plugin
Skills and agents are available immediately — no further steps needed.
agy plugin install https://github.com/epicsagas/obscura-plugin
obscura-plugin installautomatically downloads theobscuraandobscura-workerbinaries from Obscura releases. Linux requires glibc 2.35+ (Ubuntu 22.04+).
# pre-built binary, no Rust required
curl --proto '=https' --tlsv1.2 -LsSf \
https://github.com/epicsagas/obscura-plugin/releases/latest/download/obscura-plugin-installer.sh | sh
# pre-built binary, no Rust required
irm https://github.com/epicsagas/obscura-plugin/releases/latest/download/obscura-plugin-installer.ps1 | iex
brew install epicsagas/tap/obscura-plugin
# pre-built binary via Rust toolchain (fast)
cargo binstall obscura-plugin
# build from source (requires Rust toolchain)
cargo install obscura-plugin
obscura-plugin --versionto verify. Update withbrew upgrade obscura-pluginor re-run the installer script.
After installing the binary, run obscura-plugin install to connect it to your tools:
obscura-plugin install # interactive — pick which tools
obscura-plugin install cursor # Cursor
obscura-plugin install opencode # OpenCode
obscura-plugin install cline # Cline
obscura-plugin install all # all at once
obscura-plugin uninstall cursor # remove from a specific tool
obscura-plugin list # show supported tools and status
| Tool | Skills | Method |
|---|---|---|
| Claude Code | plugin auto-discovers | .claude-plugin/ manifest |
| Codex CLI | plugin auto-discovers | .codex-plugin/ manifest |
| Antigravity | plugin auto-discovers | root plugin.json |
| Cursor | ~/.cursor/rules/ | obscura-plugin install |
| OpenCode | ~/.opencode/skills/ | obscura-plugin install |
| Cline | ~/.cline/skills/ | obscura-plugin install |
Registered skills are available as slash commands inside your agent:
/obscura-fetch <url> [--dump html|text|links|markdown] [--eval <js>] [--selector <css>] [--stealth]
/obscura-scrape <url1> <url2> ... [--eval <js>] [--concurrency <N>] [--format json|text]
/obscura-pipeline <index-url> # discover links → scrape in one pipeline
/obscura-crawl <seed-url> # recursive crawl with depth control, pagination, sitemap discovery
npx claudepluginhub epicsagas/obscura-plugin --plugin obscuraAI-native publishing system — autonomous multi-phase workflows from ideation to EPUB/PDF. Fiction, non-fiction, technical, screenplay, poetry, game, academic, and custom genres.
Local-first memory server — hybrid BM25+vector search, vault management, lint, and launchd lifecycle for project knowledge.
3 commands + 19 auto-trigger skills + self-evolving agent harness. Less to remember, more automation.
Software engineering knowledge graph — design patterns, laws, refactorings, and code smells with graph traversal and AI-powered code analysis.
Auto-compress .md, .html, .txt files read by Claude Code via PostToolUse hook.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows