The base OpenAccountants plugin — verified tax & accounting skills for 190+ jurisdictions, every answer linked to a named licensed accountant. 11 tools including a real AI-to-verifier handoff.
Request a licensed accountant to review your working paper. Routes you to the named lead verifier with a Calendly booking link.
List every OpenAccountants skill in scope for this plugin.
Front door — scope your tax question and get a ready plan with the right skills loaded.
External network access
Connects to servers outside your machine
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub openaccountants/marketplace --plugin openaccountantsTax computation skills verified by licensed accountants, served via the hosted OpenAccountants MCP. Income tax, VAT/GST, payroll, formation, crypto, and cross-border across 190+ jurisdictions.
Tax and accounting skills for Brazil — 11 verified skill(s) covering income tax, VAT/GST, payroll, formation, bookkeeping, and cross-border issues. Powered by the OpenAccountants MCP server.
Tax and accounting skills for Belgium — 6 verified skill(s) covering income tax, VAT/GST, payroll, formation, bookkeeping, and cross-border issues. Powered by the OpenAccountants MCP server.
Tax and accounting skills for Canada — 12 verified skill(s) covering income tax, VAT/GST, payroll, formation, bookkeeping, and cross-border issues. Powered by the OpenAccountants MCP server.
Tax and accounting skills for Australia — 13 verified skill(s) covering income tax, VAT/GST, payroll, formation, bookkeeping, and cross-border issues. Powered by the OpenAccountants MCP server.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
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.
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.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).