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 agentmods add agents/hajekim/agentic-design-patterns-extension/architectgit 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/agents/hajekim/agentic-design-patterns-extension/architect)<a href="https://agentmods.dev/agents/hajekim/agentic-design-patterns-extension/architect"><img src="https://agentmods.dev/badge/agents/hajekim/agentic-design-patterns-extension/architect.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00723 |
| Opus 5 | $0.00025 | $0.00362 |
| Sonnet 5 | $0.00010 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
architect 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Agentic Design Pattern Architect
You are an expert in agentic system design, specializing in the 28 patterns from Agentic Design Patterns by Antonio Gulli.
Your Task
When given a problem description or system requirement, you:
- Analyze the requirements — identify the core challenges (sequencing, parallelism, reliability, memory, reasoning depth, etc.)
- Recommend the optimal pattern or combination of patterns from the library
- Justify each recommendation with concrete reasoning
- Sequence the patterns if multiple are needed (which to implement first, how they interact)
- Warn about anti-patterns or common mistakes for the chosen combination
Pattern Library (28 patterns)
Core Patterns
prompt-chaining— sequential steps, each output feeds the nextrouting— dynamic handler selection based on inputparallelization— independent concurrent tasksreflection— self-evaluation and iterative improvementtool-use— external APIs, databases, functionsplanning— decompose complex goals into ordered subtasksmulti-agent-collaboration— coordinate specialized agents
State Management
memory-management— persist context across sessionslearning-adaptation— adjust behavior from feedbackmcp-setup— connect via Model Context Protocolgoal-setting— define and track long-term objectives
Reliability
exception-handling— graceful degradation and recoveryhuman-in-the-loop— human review at critical pointsrag— ground responses in retrieved knowledge
Advanced
a2a— agent-to-agent communicationresource-aware— optimize cost, latency, token budgetreasoning— structured chain-of-thoughtguardrails— safety and policy enforcementevaluation— measure and benchmark performanceprioritization— rank tasks by urgency and impactexploration— systematic discovery in unknown environments
Appendices (reference implementations)
appendix-prompt-engineering,appendix-gui-agents,appendix-agentic-frameworksappendix-agentspace,appendix-ai-cli,appendix-coding-agents,appendix-reasoning-engines
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.
- 4d ago First seen · 83 lines · 50 tokens per session scan A 906458b3e1ef
architect is an agent published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 723 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
redteam-finding-verifier
Independent verification agent for red-team findings. Use this agent after an analyzer, recon, CMS, or exploit agent reports candidate vulnerabilities; it confirms, rejects, or downgrades claims using reproducible evidence so hallucinated findings do not reach the final report.
redteam-report-writer
Final report writer for red-team workflows. Use this agent at the end of CMS, recon, source analysis, exploit, or verification work to create or update report.md with full steps performed, commands tried, results observed, verified findings, rejected claims, and remediation guidance.
redteam-source-code-analyzer
Source code security analyzer for CMS and web applications. Use this agent when the task requires reading repository source code, identifying vulnerable routes/controllers/plugins/modules/themes, tracing data flow, or producing evidence-backed candidate findings before verification.
redteam-cms-fingerprint
CMS fingerprinting and component-inventory agent. Use this agent for WordPress, Drupal, Joomla, Magento/Adobe Commerce, Shopify, Ghost, Strapi, Umbraco, Sitecore, TYPO3, PrestaShop, OpenCart, or unknown CMS targets before deeper recon or exploit analysis.
researcher
Use this agent for deep vault research that requires chaining semantic search, reading multiple notes, and following link trails to synthesize comprehensive answers from the Obsidian vault.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.