# rohitg00/pro-workflow

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

Repository: https://github.com/rohitg00/pro-workflow
Canonical: https://ross.abutalabs.com/products/pro-workflow
Homepage: https://rohitg00.github.io/pro-workflow/infographic.html
Language: JavaScript
License Family: other
Topics: claude, claude-code, cursor, workflow, agent-orchestration, ai-agents, ai-coding, ai-workflow, claude-code-plugin, claude-code-skills, claude-skills, codex, context-engineering, developer-tools, gemini-cli, hooks, productivity, self-correction, worktrees
Last push: 2026-08-17T20:24:39+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 83, longevity 15
- inputs: {"age_days": 213, "days_push": 16, "days_rel": 116, "gap_med": 7.0, "n_releases_24m": 9}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2784, forks 273 (observed 2026-08-28T04:07:21.799714+00:00)

## What it is
A Claude Code plugin and workflow system that gives AI coding agents self-correcting persistent memory, FTS5-indexed research wikis, and quality-gate hooks backed by a single SQLite store. It ships 41 skills, 8 agents, 23 commands, and hook scripts, and works with Claude Code, Cursor, and 32+ agents via skills add.

## Use cases
- stop re-explaining coding conventions to Claude every session
- make my AI coding assistant learn from my corrections
- build a persistent searchable research wiki that grows automatically
- run parallel Claude Code sessions with git worktrees
- orchestrate agent teams and subagents in Claude Code
- track token costs and enforce quality gates on AI-generated code
- auto-research topics overnight with a budget-capped research loop

## When to choose
- you use Claude Code or Cursor daily and repeat the same corrections across sessions
- you want durable, searchable memory and research notes across AI coding sessions
- you want battle-tested workflow patterns, hooks, and skills for AI-assisted development

## When to avoid
- you don't use AI coding assistants like Claude Code or Cursor
- you need a lightweight setup without SQLite dependencies or hook scripts
- you require a permissively-audited codebase and are concerned the repo metadata lacks a license file

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, rag, developer-tools, search-engine, workflow-automation, prompt-engineering
- domain: developer-tools, artificial-intelligence
- platform: cli, cross-platform
- tags: claude-code, claude-code-plugin, cursor, self-correction, context-engineering, worktrees, hooks, sqlite-fts5, agent-teams, skills, knowledge-wiki, ai-coding-workflow, ai-agents, automation, nodejs

## Member repositories
- rohitg00/pro-workflow (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:21.799714+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:16:03.383086+00:00, confidence not recorded.
  - readme: https://github.com/rohitg00/pro-workflow (fetched 2026-08-28T04:07:21.799714+00:00, sha 86c045703228)
  - homepage: https://rohitg00.github.io/pro-workflow/infographic.html (fetched 2026-08-29T09:55:28.468144+00:00, sha cf0923cfdabc)
  - registry_npm: https://registry.npmjs.org/pro-workflow (fetched 2026-08-29T09:55:28.477402+00:00, sha 4a7c2935cd3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.