AI Agent & Automation Workflows

Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.

Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.

Use Pro Workflow when Claude Code sessions keep repeating the same mistakes and you want corrections, quality gates, and parallel worktree routines to persist across sessions instead of being re-explained every time.

Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".

LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.

Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says "I do not know this area", "give me the map", "zoom out", "orient me".

Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation.

Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.

Collaborator memory recall — restores past collaboration history at session start. Pulls relevant context from all 5 folders of 30Claude (01Sessions, 02Learnings, 04Plans, 05Research, 06Designs), with 20Wiki as secondary. USE PROACTIVELY at session start when user requests non-trivial work, reopens past project, mentions external tech by name, or says Korean "이전에 / 예전에 / 우리 ~했잖아" (English: "previously" / "earlier" / "we did this before"). Primary mechanism for continuity — ensures Claude remembers past decisions, learnings, plans, research, and designs instead of starting from zero. Max 1500 tokens injected per briefing.

Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.

Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.

Start, structure, grow, query, and maintain reusable research wikis. Use when the user wants to create a new wiki, add sources to an existing wiki, compile source material into wiki pages, customize wiki structure or flavor, generate research maps, update indexes, or maintain knowledge bases for papers, topics, projects, products, people, organizations, or ongoing research areas.

Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.