By kyletabor
Independent work verification gates for Claude Code — enforces verification at task boundaries via hooks
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
A collection of plugins for Claude Code that add structured development workflows, session management, learning tools, and productivity shortcuts. Built by Kyle Tabor for daily use -- shared publicly for anyone who wants to get more out of Claude Code.
| Plugin | Version | Status | Description |
|---|---|---|---|
| dev-process | 2.0.0 | Stable | Spec-driven development pipeline with review gates and independent verification |
| capture | 1.1.0 | Stable | Quick-capture tasks, bookmarks, ideas, and follow-ups to a personal inbox |
| handoff | 1.1.0 | Stable | Save session context and resume in a fresh Claude session without losing continuity |
| capa | 1.0.0 | Stable | Corrective and Preventive Action process for investigating broken processes |
| educate-me | 1.0.0 | Stable | Structured 1-on-1 tutor that teaches any subject using a MECE framework |
| session-historian | 1.0.0 | Stable | Read and analyze Claude Code session history for debugging and workflow analysis |
| secret-vault | 0.1.0 | Experimental | Intercept and securely store secrets pasted in chat, auto-redact from logs |
| gastown | 1.1.0 | Deprecated | Multi-agent orchestration for Gas Town environments (abandoned due to upstream bugs) |
Install all plugins from the marketplace:
claude plugin add kyletabor/claude_plugins
Install an individual plugin:
claude plugin add kyletabor/claude_plugins/dev-process
claude plugin add kyletabor/claude_plugins/capture
claude plugin add kyletabor/claude_plugins/handoff
# etc.
The single orchestrator for all non-trivial implementation work. Runs a six-phase pipeline: Architecture Spec, Spec Review, Implementation, Code Review, Testing + Independent Verification, and Ship. It coordinates sub-skills (brainstorming, TDD, subagent-driven development, verification) so you don't invoke them separately. Use it any time you're building something that touches multiple files or needs architecture before coding.
Invoke: /dev-process or just ask Claude to "implement this" / "build this feature".
Zero-friction inbox for things you want to remember later. Say "bookmark this", "add a task", "idea: ...", or "follow up on ..." and it captures the item with auto-categorization (task, bookmark, idea, follow-up, research). Backed by an MCP server with search, digest, and promotion to a full task tracker.
Invoke: /capture <text> or use natural language like "remember this for later".
Saves your current session context -- active goals, unfinished work, key files, decisions made -- so a fresh Claude session can pick up exactly where you left off. Useful when context gets long or you need to switch machines. The handoff file auto-injects on the next session start.
Invoke: /handoff or say "save context" / "pick this up later".
Corrective and Preventive Action -- an eight-phase process for when your development process itself fails. Not for simple bugs (use systematic-debugging for those). Use CAPA when the same failure pattern recurs, when "done" was claimed but the feature doesn't work, or when a gate failed to fire. Tracks root causes, research, process fixes, and re-execution in a shared SQLite database.
Invoke: /capa <what broke> or say "why did this fail again" / "do a retrospective".
A structured 1-on-1 tutor that teaches any subject step-by-step. Organizes material into a MECE (Mutually Exclusive, Completely Exhaustive) framework with 3-5 major sections, teaches one concept at a time, checks understanding before moving on, and wraps up with a vocabulary list and next steps. Works with topics, URLs, or local files.
Invoke: /educate-me <topic or URL> or say "teach me about X" / "walk me through this".
Six Python scripts for reading and analyzing Claude Code session history stored in ~/.claude/projects/. List recent sessions, search conversation text, find errors, get deep context for debugging, and run cross-session pattern analysis. Useful for understanding what past agents did, continuing interrupted work, or spotting recurring failure patterns.
Invoke: /session-historian or ask "what did the last session do" / "find sessions about X".
Early-stage plugin for intercepting secrets (API keys, tokens, passwords) pasted into chat and storing them securely in ~/.secrets/ with restricted permissions. Includes a UserPromptSubmit hook that catches common secret patterns automatically. Not yet feature-complete -- use with the understanding that the redaction and storage mechanisms are still being hardened.
Invoke: /secret for the guided flow, or paste a secret and the hook catches it.
npx claudepluginhub kyletabor/claude_plugins --plugin verification-hooksCorrective and Preventive Action (CAPA) process skill. Investigates process failures, researches best practices, fixes the process first, then re-executes to fix the original defect. Includes SQLite tracking database for pattern analysis across incidents.
Quick-capture tasks, bookmarks, ideas, follow-ups, and research items to a personal inbox via the capture-mcp MCP server.
Read and analyze Claude Code session history for debugging, continuity, and workflow analysis
Tmux session control for Claude Code — launch test sessions, send commands, read output with multi-agent safety
Save session context and resume in fresh Claude sessions without losing continuity
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Verifiable AI-Augmented Engineering framework with traceable requirements, independent verification, and compliance-ready artifacts
Framework for AI-powered multi-step workflows with quality gates
Plan iron, verify real. Ironclad planning with independent verification chain. Turns any input into a bulletproof plan, executes with TDD, verifies with independent agents.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more