pro-workflow

One SQLite store under every Claude Code session: corrections become FTS5-searchable rules that auto-load, research grows persistent wikis, and 37 hook scripts add quality gates.

2,617 253 JavaScriptupdated 3 days ago

coding memory

View on GitHub Dispute this mapping →

Curator's take

The most complete attack on Claude Code amnesia we've mapped: correct it once and the correction becomes a durable, searchable rule; research lands in wikis that persist and even grow via an auto-research loop; hooks add git/secret guards and cost tracking. After 50 sessions the compounding is real. Two cautions: NO license file at review time (all rights reserved by default — same gap as this author's other tools), and 34 skills + 37 hooks is a lot of surface — adopt the memory core first, audit the hooks before letting them gate your commits.

Mapped by ShipWithAI editors · links verified

README.md

Your Claude Code gets smarter every session.

Self-correcting memory + persistent FTS5-indexed wikis + auto-research loop, all on one SQLite store.
Correct Claude once — it never repeats the mistake. Build a wiki on a topic — it grows itself overnight.
34 skills • 8 agents • 22 commands • 37 hook scripts across 24 events
Works with Claude Code, Cursor, and 32+ agents via SkillKit.

The Problem

You correct Claude the same way 50 times. You explain conventions every new session. Context compacts, learnings vanish, mistakes repeat. You research the same topic in three different sessions because there is nowhere durable for the answers to land.

Every Claude Code user hits this wall.

The Solution

Pro Workflow puts a single SQLite store underneath every session.

Self-correction memory — every correction becomes a rule, FTS5-searchable, auto-loaded on session start.
Knowledge plane — persistent research wikis on disk + FTS5 shadow index, queryable from any session, optionally grown by an auto-research loop.
Quality gates — LLM-powered hooks, deterministic git/secret guards, compaction-aware state, cost tracking.

After 50 sessions you barely correct anything. After a week of auto-research, your wiki on a topic is denser than the curated lists you started from.

Self-Correction Loop

Session 1:  You → "Don't mock the database in tests"
            Claude → Proposes rule → You approve → Saved to SQLite

Session 2:  SessionStart loads all learnings + lists your wikis
            UserPromptSubmit auto-injects top wiki hits when relevant
            Claude writes integration tests, cites the right wiki page

Session 50: Correction rate near zero. Wiki has 200 cited claims.

Install

Pro Workflow is published in two places: the Claude Code plugin marketplace (native), and SkillKit (cross-agent translator). Other agents do not have first-class plugins yet — SkillKit translates the skill bundle into each agent's native skill format.

Claude Code (native)

/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow

Cursor, Codex, Copilot CLI, Droid, Gemini CLI, OpenCode, and 26 more (via SkillKit)

SkillKit translates the 34 skills + 22 commands into each agent's native skill format and drops them in the right config directory.

npx skillkit install rohitg00/pro-workflow --agent <name> --force

Notes:

Use rohitg00/pro-workflow (the GitHub form), not the bare name — skillkit install resolves providers from owner/repo, not marketplace slugs.
--force is currently required: SkillKit's security scanner has open false positives

Continue your stack

What teams reach for next — and why each earns a place beside pro-workflow. Ranked by curator confidence.

Pairs well with

skillkit

Package manager for AI agent skills — install from 400K+ skills across 31 sources, auto-translate between 46 agents' incompatible formats, security-scan on install, sync to every agent at once.

Why it fitspro-workflow ships its 34 skills through SkillKit — the package manager is its distribution channel to 32+ agent formats.

Alternative to See all + compare →

claude-reflect

Claude Code plugin that learns from your corrections — hooks capture them in-session, /reflect syncs approved learnings to CLAUDE.md/AGENTS.md, /reflect-skills mines history into reusable commands.

Why it fitsSame core job — corrections that stick across Claude Code sessions. claude-reflect is the focused plugin (corrections → CLAUDE.md); pro-workflow builds a whole SQLite-backed memory-and-hooks platform around the idea.

ECC

Cross-harness 'operating system' for coding agents — 268 skills, 66 agents, hooks, rules, memory persistence, instinct-based continuous learning and AgentShield security scanning. MIT.

Why it fitsSame job — a persistent operating layer under coding-agent sessions with hooks, learned rules and quality gates. pro-workflow is one SQLite store focused on Claude Code; ECC is the maximalist cross-harness system spanning 7+ harnesses with skills, agents and security tooling.

opencode-mem

OpenCode plugin giving coding agents persistent cross-session memory — local SQLite + vector search, automatic memory capture, user-profile learning, and a web UI. Nothing leaves your machine.

Why it fitsSame job on rival harnesses: a persistent local store under every coding-agent session. pro-workflow puts SQLite + FTS5 rules under Claude Code; opencode-mem puts SQLite + vector recall with auto-capture under OpenCode.