# Agentic Engineering

## Docs

- [Dojo](https://agentic.proxify.io/dojo/index.md): Hands-on exercises, downloadable skills, and guided builds.
- [Collections](https://agentic.proxify.io/explore/collections.md): Curated indexes and awesome lists covering the full Claude Code ecosystem.
- [Slash Commands](https://agentic.proxify.io/explore/commands.md): Production-ready slash command suites for structured Claude Code workflows.
- [Awesome Claude Code](https://agentic.proxify.io/explore/index.md): Community-curated skills, plugins, tools, and collections — sorted by stars.
- [Memory & Context](https://agentic.proxify.io/explore/memory.md): Plugins that persist, compress, and inject session context across conversations.
- [Orchestration](https://agentic.proxify.io/explore/orchestration.md): Multi-agent systems, harnesses, and coordination frameworks for Claude Code.
- [Skills](https://agentic.proxify.io/explore/skills.md): Individual skill packages installable via npx skills add.
- [Tools & Harnesses](https://agentic.proxify.io/explore/tools.md): Desktop apps, CLIs, MCP servers, and full harness setups for Claude Code.
- [Agentic Fast Track](https://agentic.proxify.io/index.md): Proxify's Claude Code acceleration toolkit — skills, agents, and guides for agentic engineering.
- [Agent Teams](https://agentic.proxify.io/patterns/agent-teams.md): When and how to use Agent Teams — the decision framework, delegate mode, and practical advice.
- [Agentic Engineering](https://agentic.proxify.io/patterns/agentic-engineering.md): The shift from coding with AI assistance to delegating work to AI agents.
- [Autonomous Task Patterns](https://agentic.proxify.io/patterns/autonomous-tasks.md): How to set Claude up to work without supervision — and the guardrails that make it safe.
- [Context Management](https://agentic.proxify.io/patterns/context-management.md): How to keep Claude Code effective across long sessions and large codebases.
- [Cost & Model Routing](https://agentic.proxify.io/patterns/cost-and-model-routing.md): How to route models strategically and control token costs across multi-agent workflows.
- [Context Distribution](https://agentic.proxify.io/patterns/distribution.md): How knowledge reaches agents at the right time — the layered architecture behind CLAUDE.md, skills, agents, and why each exists.
- [Invocation Quality](https://agentic.proxify.io/patterns/invocation-quality.md): Most subagent failures are bad prompts, not bad agents. How to write invocations that succeed.
- [The Maturity Ladder](https://agentic.proxify.io/patterns/maturity-ladder.md): Four levels of working with AI — from vibe coding to production-grade engineering.
- [Orchestration Patterns](https://agentic.proxify.io/patterns/orchestration-patterns.md): Proven patterns for coordinating multiple agents — from simple fan-out to contract chains for reliable parallel integration.
- [Builder-Validator Pairs](https://agentic.proxify.io/patterns/orchestration-patterns/builder-validator.md): A builder implements; a read-only validator checks. Restricting tools forces issues to be surfaced, not silently fixed.
- [Contract Chains / Wave Execution](https://agentic.proxify.io/patterns/orchestration-patterns/contract-chains.md): Run parallel work in waves — each wave's concrete outputs become the contracts for the next.
- [Fan-Out / Fan-In](https://agentic.proxify.io/patterns/orchestration-patterns/fan-out-fan-in.md): Spawn N independent agents in parallel, then synthesize their results.
- [Pipeline Chains](https://agentic.proxify.io/patterns/orchestration-patterns/pipeline-chains.md): Sequential stages where each phase's output feeds the next, with context reset between stages.
- [Supervisor / Team Lead](https://agentic.proxify.io/patterns/orchestration-patterns/supervisor.md): The main session coordinates exclusively while teammates implement.
- [Parallel Execution](https://agentic.proxify.io/patterns/parallel-execution.md): Running multiple Claude agents on the same project — worktree isolation, scoping strategies, and conflict resolution.
- [Permission Modes](https://agentic.proxify.io/patterns/permission-modes.md): Five permission modes as workflow optimization — not just security settings.
- [Permutation Frameworks](https://agentic.proxify.io/patterns/permutation-frameworks.md): A three-phase system for consistent, repeatable code generation at scale.
- [Prompting Craft](https://agentic.proxify.io/patterns/prompting-craft.md): Specific techniques for getting more out of Claude Code — not generic prompt engineering.
- [Robots-First Engineering](https://agentic.proxify.io/patterns/robots-first.md): Designing specs, code, and workflows for agent execution — not human execution.
- [The Self-Improving Loop](https://agentic.proxify.io/patterns/self-improving-loop.md): How to make Claude Code get better at your project over time — not just within a session.
- [Session Management](https://agentic.proxify.io/patterns/session-management.md): When to start fresh, how to hand off context, and how to juggle multiple sessions.
- [Subagent Patterns](https://agentic.proxify.io/patterns/subagent-patterns.md): When and how to use subagents to parallelize work while keeping your main context clean.
- [The Supply Chain](https://agentic.proxify.io/patterns/supply-chain.md): Who controls each instruction layer — and what happens when one is compromised.
- [System Evolution](https://agentic.proxify.io/patterns/system-evolution.md): Every bug teaches your system something. Trace, patch, never repeat.
- [Workflow Patterns](https://agentic.proxify.io/patterns/workflow-patterns.md): Proven patterns for working with Claude Code on real engineering tasks.
- [Common Pitfalls](https://agentic.proxify.io/reference/common-pitfalls.md): Mistakes engineers make when starting with Claude Code — and how to avoid them.
- [Links & Resources](https://agentic.proxify.io/reference/links.md): Curated links for engineers adopting Claude Code.
- [Onboarding Checklist](https://agentic.proxify.io/reference/onboarding-checklist.md): Quick-start checklist for engineers setting up Claude Code — all actions, no explanations.
- [Writing CLAUDE.md](https://agentic.proxify.io/setup/claude-md.md): How to write effective CLAUDE.md files — the highest-leverage configuration surface for Claude Code.
- [Hooks Playbook](https://agentic.proxify.io/setup/hooks-playbook.md): Hook composition patterns, governance strategies, and the enforcement ladder — the opinion layer on top of the official docs.
- [Make It Yours](https://agentic.proxify.io/setup/make-it-yours.md): Create a personal plugin workspace — your portable Claude configuration that follows you across every project.
- [MCP Wiring](https://agentic.proxify.io/setup/mcp-wiring.md): How MCP connections compose with CLAUDE.md, skills, and hooks — the opinion layer on top of the official docs.
- [Composing a Skills Stack](https://agentic.proxify.io/setup/skills-stack.md): How to discover, install, and compose skills into a layered knowledge system for your project.

## OpenAPI Specs

- [openapi](https://agentic.proxify.io/api-reference/openapi.json)