pro-workflow

---

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.

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 skills add (cross-agent installer). Other agents do not have first-class plugins yet — skills add installs the skill bundle into each agent's native skill directory.

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 skills add)

skills add installs the 41 skills + 23 commands into each agent's native skill directory.

npx skills add rohitg00/pro-workflow

Notes:

• Use rohitg00/pro-workflow (the GitHub form), not the bare name — skills add resolves providers from owner/repo, not marketplace slugs.

Works with these agents: cursor, codex, gemini-cli, opencode, github-copilot, droid (factory), antigravity, amp, clawdbot, cline, codebuddy, commandcode, continue, crush, goose, kilo, kiro-cli, mcpjam, mux, neovate, openhands, pi, qoder, qwen, roo, trae, universal, vercel, windsurf, zencoder.

Roster notes (2026): windsurf relaunched as Devin Desktop, which speaks the Agent Client Protocol (ACP); gemini-cli was superseded by the Antigravity CLI for consumers. The adapter names above still resolve, but target the current product. MCP works across every agent in this list with the same setup. See references/modern-workflows-2026.md for the interop picture.

After install, run skills sync to register the skills with the target agent's config.

If neither path works for your setup, clone and copy the bundle directly. Adjust the destination to your agent's skill directory (e.g. ~/.cursor/rules/, ~/.gemini/extensions/, etc.).

git clone https://github.com/rohitg00/pro-workflow.git /tmp/pw
cd /tmp/pw && npm install && npm run build

cp -r /tmp/pw/templates/split-claude-md/* ./.claude/
cp -r /tmp/pw/skills    ~/.claude/skills/
cp -r /tmp/pw/commands  ~/.claude/commands/
cp    /tmp/pw/hooks/hooks.json ~/.claude/hooks.json

First-run smoke test

/doctor              # confirms SQLite store, hooks, skills load
/wrap-up             # runs the end-of-session ritual (no-op on fresh install)

If /doctor reports KB: missing, run cd ~/.claude/plugins/*/pro-workflow && npm install && npm run build — the SQLite components need a build step a handful of marketplaces skip.

---

What to type first

After install you have 41 skills and 23 slash commands. You don't need to memorize them; the agent picks the right skill from your prompt. The five commands below cover 80% of daily use:

When	Command	What it does
Wrong correction repeats	/learn-rule	Capture the correction as a rule. Loaded on every future SessionStart.
End of a coding session	/wrap-up	Audit changes, persist learnings, write a handoff doc.
Researching a topic	/wiki init <slug>	Spin up a persistent FTS5 wiki. Auto-injected when you mention the topic later.
Stuck on a hard bug	/develop	Research → Plan → Implement phases with validation gates.
Before a PR	/smart-commit	Quality gates, staged review, conventional commit message.

Full list: commands/ · skills/ · /list inside any session.

---

60-second tour

# 1. Self-correction (existing)
/learn-rule          # capture a correction
/wrap-up             # end session, persist learnings, audit changes
/insights            # heatmaps, trends, productivity

# 2. Knowledge plane (v3.3, new)
/wiki init agent-memory --title "Agent Memory" --flavor research
/wiki page agent-memory wiki/concepts/episodic-memory.md --type concept
/wiki ask "what is episodic memory" --wiki agent-memory

# 3. Auto-research (budget-capped, opt-in)
/wiki seed agent-memory "memory consolidation in agents"
/wiki research agent-memory --max-pages 5 --budget-usd 0.50

# 4. Hybrid retrieval (BM25 + vector RRF, optional)
/wiki embed agent-memory                       # OPENAI_API_KEY or VOYAGE_API_KEY
/wiki hybrid "consolidation patterns" --wiki agent-memory

# 5. Multi-LLM deliberation (transcript persists as a wiki page)
/wiki council "should we adopt episodic memory?" --wiki agent-memory

# 6. Browse the wiki visually (single-file HTML, S3-shareable)
/wiki view agent-memory
open ~/.pro-workflow/wikis/agent-memory/derived/viewer.html

# Kill switch for any auto loop
touch ~/.pro-workflow/STOP

UserPromptSubmit auto-loads top-3 wiki hits when prompts mention indexed topics. SessionStart lists registered wikis and recent learnings.

---

What's new in v3.3

Persistent knowledge plane on top of self-correction memory.

Skill	Purpose
wiki-builder	Persistent FTS5-indexed research wikis. 9 flavors: research, paper, domain, product, person, organization, project, codebase, incident. Path-traversal-guarded.
wiki-query	BM25 retrieval with snippets. ask, related, show. Auto-injects on UserPromptSubmit.
wiki-research-loop	Budget-capped BFS. Pluggable source fetchers (web/arXiv/GitHub + custom). Convergence detection, kill-switch, atomic seed claim, try/finally state guards.
llm-council	Provider-agnostic 3-phase deliberation (Anthropic/OpenAI/OpenRouter/Fireworks/custom). Promise.allSettled so one provider failure doesn't abort the run. Transcript persists as a wiki page.
survey-generator	Provider-agnostic literature survey. Output target = wiki markdown page. Bibliography validation (uniqueness + section-paper refs), citation IDs aligned with sources.md rows.
wiki-viewer	Single-file HTML viewer for any wiki: pages + sources + seeds + link graph + in-browser search + "copy as seed" CTAs. S3-shareable. Applied lessons from Thariq Shihipar's HTML-as-output thesis.

Plus: /wiki command (now with view), learn-rule Wiki: <slug> scoping, schema additions (wikis, wiki_pages + FTS5, wiki_sources, wiki_claims, wiki_seeds, wiki_embeddings, learnings_wiki), reactive file-watcher seed enqueue, cron-tick driver, /doctor extended with KB + provider sections.

---

Comparison

Feature	Pro Workflow	Superpowers	ECC	gstack	GSD
Self-correcting memory (SQLite + FTS5)	Yes	No	No	No	No
Persistent research wikis (FTS5)	Yes	No	No	No	No
Auto-research loop (budget-capped BFS)	Yes	No	No	No	No
Hybrid retrieval (BM25 + vector + RRF)	Yes	No	No	No	No
Multi-provider LLM council	Yes	No	No	No	No
LLM-powered hooks (type: "prompt")	Yes	No	No	No	No
Permission denial analysis	Yes	No	No	No	No
Compaction-aware state preservation	Yes	No	No	No	No
Cost tracking and budget alerts	Yes	No	No	No	No
MCP overhead auditing	Yes	No	No	No	No
Cross-agent (32+ agents via skills add)	Yes	No	Some	No	No
Skills	34	14	140+	18+	0
Agents	8	5	36	0	18
Commands	22	3	60+	5+	57
Hook events	24	8	18	0	0

---

What's inside

41 skills

Knowledge plane (new in v3.3)

Skill	What it does
wiki-builder	Scaffold + register FTS5-indexed research wikis
wiki-query	BM25 retrieval, snippets, related, show
wiki-research-loop	Budget-capped BFS over web/arXiv/GitHub fetchers
llm-council	Provider-agnostic 3-phase multi-LLM deliberation
survey-generator	Literature survey artifact, output to a wiki page
wiki-viewer	Single-file HTML viewer (pages, sources, seeds, link graph, search)

Quality gates and observability

Skill	What it does
smart-commit	Quality gates, staged review, conventional commits
llm-gate	AI-powered commit and secret hooks (type: "prompt")
permission-tuner	Analyze denials, generate allow/deny rules
compact-guard	State preservation through compaction cycles
cost-tracker	Session cost awareness with budget benchmarks
mcp-audit	MCP server token-overhead analysis
token-efficiency	Anti-sycophancy + tool-call budgets + read-before-write
safe-mode	Guardrails for destructive operations