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-skills --skill learning-adaptationgit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skillsWrote 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-skills/learning-adaptation)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/learning-adaptation"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/learning-adaptation/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-skills/learning-adaptation"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/learning-adaptation.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 | $0.00443 | $0.03918 |
| Opus 5 | $0.00221 | $0.01959 |
| Sonnet 5 | $0.00089 | $0.00784 |
| Haiku 4.5 | $0.00044 | $0.00392 |
Grade A, and why
learning-adaptation 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- learning-adaptation — 100% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning and Adaptation Pattern
Overview
The Learning and Adaptation Pattern enables agents to improve their performance over time by learning from experience, feedback, and new data. Unlike static agents that follow fixed rules, adaptive agents evolve — refining their strategies, expanding their knowledge, and improving their decision-making based on what they observe in their environment.
Core Principle: Agents that learn from experience become better over time — evolving from rule-followers to genuine problem-solvers.
When This Skill Applies
Activate this pattern when:
- Agent performance must improve autonomously without constant manual intervention
- The environment changes and the agent must adapt to new conditions
- Feedback from interactions should influence future behavior
- The agent needs to generalize from past experiences to novel situations
- Personalization requires learning individual user preferences over time
- The agent must distinguish between successful and unsuccessful strategies
Rule of thumb: Use Learning and Adaptation when the agent needs to become smarter from doing, not just from being told.
Learning Mechanisms
1. Reinforcement Learning (RL)
Agents try actions and receive rewards for positive outcomes, penalties for negative ones:
- Application: Robotics, game-playing agents, optimization tasks
- Key algorithms: PPO (Proximal Policy Optimization), DPO (Direct Preference Optimization)
- Strength: Learns optimal behaviors in complex, sequential decision environments
2. Supervised Learning
Agents learn from labeled examples — input → desired output mappings:
- Application: Classification, prediction, decision support
- Strength: High accuracy on known task categories with labeled training data
3. Few-Shot / Zero-Shot Learning with LLMs
LLM-based agents adapt to new tasks with minimal examples or clear instructions:
- Application: Rapid adaptation to new domains or task formats
- Strength: No fine-tuning required — in-context learning from examples
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.
- 8d ago First seen · 396 lines · 443 tokens per session scan A 4605d739af81
learning-adaptation is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 443 tokens to every session and 3,918 once invoked, about $0.0022 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 skills, from other repositories
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
gemini-api
Google Gemini API patterns for Python and TypeScript. Covers content generation, streaming, tool use (function calling), vision, system instructions, context caching, batch requests, and agent workflows. Use when building applications with the Gemini API or Google Generative AI SDKs.
image-prompt
A Korean-language skill that turns a rough image idea into a detailed prompt for gpt-image-2, OpenAI’s image-generation model.
cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
data-scraper-agent
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when…
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.