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 instructions/gtesei/agentic_design_patterns/agents-mdgit clone --depth 1 https://github.com/gtesei/agentic_design_patternsWhat 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 | $0.03822 | $0.03822 |
| Opus 5 | $0.01911 | $0.01911 |
| Sonnet 5 | $0.00764 | $0.00764 |
| Haiku 4.5 | $0.00382 | $0.00382 |
Grade A, and why
agentic_design_patterns AGENTS.md 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 2d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Single source of truth for any AI agent working in this repository — Claude Code, OpenAI Codex, Aider, Cursor, Continue, etc. Repo guide + collaboration model + working conventions + project state. Read this first before making changes. Last updated 2026-05-17.
This file follows the AGENTS.md convention so any compliant agent picks it up automatically. There is no CLAUDE.md, CODEX.md, or other vendor-specific variant — AGENTS.md is the only file.
1. Repository purpose & layout
Educational, hands-on catalog of agentic-AI design patterns. Originally Python (LangChain / LangGraph); a curated TypeScript track now mirrors the entire foundational pattern set 1:1. Each pattern is self-contained, runnable, and accompanied by a long-form README.md. Reference material, not a deployable app.
Patterns live in 7 top-level category directories:
foundational_design_patterns/{1_prompt_chain, 2_routing, 3_parallelization, 4_reflection, 5_tool_use, 6_planning, 7_multi_agent_collaboration, 8_react, 9_rag, 10_hitl, 11_structured_outputs, 12_computer_use}reasoning/{tree_of_thoughts, graph_of_thoughts, deep_research}reliability/{error_recovery, guardrails}orchestration/{goal_management, subagents, skills, agent_communication, mcp, prioritization}observability/{evaluation_monitoring, resource_optimization}memory/{memory_management, context_management}learning/adaptive_learning
Each pattern dir has its own pyproject.toml, uv.lock, run.sh, README.md, QUICK_START.md, and src/ with example scripts (*_basic.py, *_advanced.py, or variants like _plan_and_act.py / _hiplan.py). Pattern packages all declare name = "agentic_design_patterns" but they are independent uv environments, not a single workspace — cd into the specific dir to install/run/lint.
TypeScript ports live under <pattern>/typescript/ for every pattern in foundational_design_patterns/. A single bun workspace with shared config lives in typescript_base/ (contains package.json, tsconfig.base.json, TYPESCRIPT.md) and covers all foundational TypeScript packages via the ../foundational_design_patterns/*/typescript glob.
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.
- 2d ago First seen · 266 lines · 3,822 tokens per session scan A 8d32ab0a59ac
agentic_design_patterns AGENTS.md is an instructions file published in the GitHub repository gtesei/agentic_design_patterns (19 stars, last pushed 2mo ago), licensed MIT. It adds 3,822 tokens to every session, about $0.0191 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 2026-08-30.
Other instructions, from other repositories
gflow-cli AGENTS.md
Instructions for ffroliva/gflow-cli, covering agents.md — gflow-cli, project at a glance, headed-browser dependency (architectural reality), dev environment tips and testing instructions — the impeccable routine.
gflow-cli CLAUDE.md
Instructions for ffroliva/gflow-cli, covering claude.md, what this project is, on every session start, claude-code-specific and mcp github tool — pr body rule (non-negotiable).
gflow-cli copilot-instructions.md
Instructions for ffroliva/gflow-cli: Review this repository as a Python CLI that automates browser-authenticated Google Flow workflows. Treat auth, browser automation, CI, release, and secret handling changes as high-risk even when the diff is small.
redux-saga-skill AGENTS.md
Instructions for anivar/redux-saga-skill, covering redux-saga — complete guide, abstract, 1. effects & yielding, rule: always yield effects and rule: use call() for async functions.
self-discover-skill CLAUDE.md
Instructions for Thomaszhou22/self-discover-skill: This project includes the SELF-DISCOVER Reasoning Skill.
self-discover-skill GEMINI.md
Instructions for Thomaszhou22/self-discover-skill: This project includes the SELF-DISCOVER Reasoning Skill.