By josix
Coordinate complex coding tasks by delegating to specialist AI agents for exploration, planning, implementation, and verification, with automated quality gates (lint, test, build) and interactive documentation generation.
Parse Claude Code session transcripts offline and surface subagent behavior metrics,
Gather comprehensive codebase context using parallel exploration agents
Generate an interactive one-module explainer for a topic — Riko gathers code scope, Senku plans a 3-5 screen teaching arc, Speedwagon authors the HTML, assembler produces explain-out/index.html
Coordinate complex tasks through sequential delegation to specialist agents.
Coordinate complex tasks through sequential delegation to specialist agents, with PARALLEL execution of Review + Verification phases using Agent Teams when available.
Use this agent when running tests and validation, verifying builds, checking type compilation, or performing final quality gates.
Use this agent when reviewing code for quality, running static analysis, checking security, or verifying adherence to patterns.
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
Use this agent when exploring the codebase for information, finding files, understanding patterns, or gathering context.
Use this agent when planning implementation strategy, analyzing requirements, designing approaches, or creating task breakdowns.
This skill should be used when handling agent model selection, tool access permissions, behavioral guardrails, MCP tool preferences, or any question about what agents can/cannot do.
Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project. Also trigger when users mention 'turn this into a course,' 'explain this codebase interactively,' 'teach this code,' 'interactive tutorial from code,' 'codebase walkthrough,' 'learn from this codebase,' or 'make a course from this project.' This skill produces a stunning, self-contained HTML file with scroll-based navigation, animated visualizations, embedded quizzes, and code-with-plain-English side-by-side translations.
This skill should be used when exploring codebases, finding patterns, searching for code, gathering context, or understanding code structure before planning or implementation.
This skill should be used when querying the graphify knowledge graph for structural codebase information, choosing between graph tools and grep, or interpreting graph query results.
This skill should be used when querying the user's personal knowledge base (cross-project personal knowledge graph) for prior learnings, notes, or decisions that apply across projects.
Matches all tools
Hooks run on every tool call, not just specific ones
Admin access level
Server config contains admin-level keywords
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.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Transform Claude Code into a multi-agent orchestrated system with verification gates.
| Requirement | Version | Purpose |
|---|---|---|
| Claude Code CLI | latest | Plugin host |
| Bash | 4+ | Hook scripts |
jq | any | Plugin validation + hook scripts |
git | any | Installation |
Python 3.9+ with graphifyy[mcp] | optional | Knowledge graph queries (install via pipx install graphifyy && pipx inject graphifyy mcp) |
/plugin marketplace add josix/agent-flow
/plugin install agent-flow@josix-plugins
claude --plugin-dir /path/to/agent-flow
git clone https://github.com/josix/agent-flow.git
cd agent-flow
claude --plugin-dir .
New to agent-flow? Walk through your first orchestration — a fresh-repo demo that exercises all 5 agents end-to-end.
Before running your first orchestration, verify the plugin is wired up correctly:
bash scripts/validate-plugin.sh
The script runs 14 structural checks covering:
plugin.json and hooks/hooks.json are valid JSONvalidate-changes.sh guardrails: path traversal, sensitive files, and system paths are blocked; valid writes are allowedensure-gitignore.sh, verify-completion.sh, dispatch-codex-review.sh, and init-state escapingIf all checks pass, you see: ✓ All tests passed.
Gather comprehensive codebase context using parallel exploration agents. Creates a reusable context file that accelerates subsequent orchestration tasks.
/deep-dive # Full codebase exploration
/deep-dive --focus=src/auth # Focus on specific path
/deep-dive --refresh # Refresh existing context
Output: .claude/deep-dive.local.md - Ephemeral, session-scoped context file
Workflow:
Integration with /orchestrate:
/orchestrate --use-deep-dive Add user authentication
When used with --use-deep-dive, orchestration leverages existing context to skip redundant exploration.
Coordinate complex multi-step tasks through the agent system. This command delegates to specialist agents in sequence:
/orchestrate Add user authentication with JWT tokens
/orchestrate --use-deep-dive Add user profile page # Use existing deep-dive context
Arguments:
--use-deep-dive: Use existing deep-dive context for accelerated explorationNote: Planning and verification are handled by agents (Senku, Alphonse) within the orchestration workflow rather than as standalone commands. This prevents responsibility conflicts in multi-agent coordination.
Execute complex tasks with parallel review and verification using Agent Teams. This command follows the same workflow as /orchestrate but runs Lawliet (review) and Alphonse (verification) concurrently after implementation, reducing wall-clock time by 30-40%.
/team-orchestrate Add user authentication with JWT tokens
/team-orchestrate --use-deep-dive Add user profile page
/team-orchestrate --force-sequential Add feature # Fall back to sequential mode
npx claudepluginhub josix/agent-flow --plugin agent-flowResearch-and-engagement assistant for contributing to open-source projects (e.g. apache/airflow, apache/spark) — draft-only, human-in-the-loop.
A 24-week Japanese listening and speaking learning plugin for Chinese-speaking learners, powered by Claude Code agents.
Adaptive running training plugin: VDOT-based pace prescription, polarized 80/20 periodization, post-workout iteration.
GTD-grounded task manager that ingests tasks from local markdown across configurable domains (five built-in, extensible via /add-domain), produces ranked daily and weekend plans via a fixed priority ladder, and one-way syncs tasks into a private GitHub Project.
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
20 SEO/GEO skills and 5 commands on one shared contract for keyword research, content creation, technical audits, schema markup, monitoring, quality gates, entity truth, and campaign memory.
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications