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 learning-adaptationgit 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/learning-adaptation)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/learning-adaptation"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/learning-adaptation.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 5.1 | $0.00443 | $0.03919 |
| 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 6d 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 learning-adaptation — 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 — 397 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.
- 6d ago First seen · 397 lines · 443 tokens per session scan A 26d5b2177035
learning-adaptation is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 443 tokens to every session and 3,919 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to learning-adaptation, 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-source-audit
Focused source-code security review workflow for web applications, CMS extensions, APIs, and supporting services.
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.