Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hajekim/agentic-design-patterns-extension --skill appendix-agentic-frameworksgit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extensionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-agentic-frameworks)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-agentic-frameworks"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/appendix-agentic-frameworks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/appendix-agentic-frameworks"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/appendix-agentic-frameworks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00412 | $0.03650 |
| Opus 5.5 | $0.00165 | $0.01460 |
| Sonnet 5.5 | $0.00082 | $0.00730 |
| Haiku 4.5 | $0.00041 | $0.00365 |
Grade A, and why
appendix-agentic-frameworks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to appendix-agentic-frameworks — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appendix C - Quick Overview of Agentic Frameworks
Overview
The Agentic Frameworks landscape provides developers with structured tools for building, orchestrating, and deploying AI agents. Each framework operates at a different level of abstraction and optimizes for different design priorities — understanding their trade-offs is essential for building reliable, maintainable agent systems.
This appendix provides a comparative overview of the major frameworks: LangChain, LangGraph, Google ADK, CrewAI, Microsoft AutoGen, LlamaIndex, and Haystack — when to use each, their core abstractions, and key code patterns.
Core Principle: No framework is universally best — choose based on whether your workflow is linear (LangChain), cyclical (LangGraph), team-based (ADK/CrewAI), or data-intensive (LlamaIndex).
Framework Comparison Matrix
| Framework | Core Abstraction | Workflow Type | State Management | Best For |
|---|---|---|---|---|
| LangChain | Chain (LCEL) | Linear DAG | Stateless per run | Simple pipelines, RAG, extraction |
| LangGraph | Graph of nodes | Cyclical + loops | Explicit, persistent | Complex agents, tool loops, HITL |
| Google ADK | Agent team | Orchestrated multi-agent | Implicit (framework) | Production multi-agent systems |
| CrewAI | Agent + Task + Crew | Sequential/hierarchical | Role-based | Team simulation, research workflows |
| AutoGen | Conversational agents | Conversation-driven | Conversational | Dynamic multi-agent conversations |
| LlamaIndex | Data pipeline | RAG-focused | Index-based | Knowledge-intensive agents, RAG |
| Haystack | Pipeline nodes | Modular search | Search-optimized | Enterprise search, QA systems |
When This Skill Applies
Activate this framework selection guide when:
- Starting a new agent project and choosing the technology stack
- Migrating from one framework to another
- Debugging framework-specific behavior or limitations
- Combining multiple frameworks in a hybrid architecture
- Evaluating build-vs-buy for agentic infrastructure
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 375 lines · 412 tokens per session scan A 1cef80579caf
appendix-agentic-frameworks is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 6mo ago), licensed MIT. It adds 412 tokens to every session and 3,650 once invoked, about $0.0016 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to appendix-agentic-frameworks, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
prompt-engineering
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
redteam
Expertise in offensive security research, vulnerability analysis, CMS-focused application testing, and red team operations.
redteam-cms
Focused methodology for authorized CMS fingerprinting, component inventory, misconfiguration review, and vulnerability validation.
redteam-exploit-validation
Focused workflow for validating exploitability safely and turning candidate issues into reproducible, bounded proof.
redteam-recon
Focused reconnaissance workflow for authorized security assessments, bug bounty triage, lab targets, and CTF infrastructure.
redteam-reporting
Focused reporting workflow for converting verified red-team work into clear, reproducible assessment artifacts.