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 skills/saski/arnesto/ai-patternsnpx skills add saski/arnesto --skill ai-patternsgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/ai-patterns)<a href="https://agentmods.dev/skills/saski/arnesto/ai-patterns"><img src="https://agentmods.dev/badge/skills/saski/arnesto/ai-patterns.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 | $0.00040 | $0.01263 |
| Opus 5 | $0.00020 | $0.00632 |
| Sonnet 5 | $0.00008 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
ai-patterns 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.
This is a copy
100% identical to ai-patterns — 0 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Patterns Reference
Patterns for effective AI-augmented software development by Lada Kesseler (github nickname lexler), Llewellyn Falco, Ivett Ördög, and Nitsan Avni.
First Step: Ensure Repository Exists and Update
~/.claude/skills/ai-patterns/scripts/ensure-patterns-repo
Patterns Location
Base path: ~/.cache/claude-skills/augmented-coding-patterns/documents
Context Management
Managing AI context, knowledge, and focus.
Obstacles
- context-rot - Earlier instructions lose influence as conversation grows
- cannot-learn - LLMs can't learn from interactions; fixed weights prevent adaptation
- limited-context-window - Fixed context size forces choices about what to keep loaded
- limited-focus - Too much context causes diluted or misdirected attention
- excess-verbosity - AI defaults to verbose output with low signal-to-noise ratio
Anti-patterns
- distracted-agent - Using one agent for everything spreads attention; instructions inconsistently followed
Patterns
- context-management - Treat context as scarce resource requiring active append/reset operations
- knowledge-document - Save important information as markdown files for session loading
- ground-rules - Essential behavioral rules auto-loaded into every session
- extract-knowledge - Save emerging insights and corrections from ephemeral context to files immediately during sessions
- focused-agent - Single narrow responsibility gives AI cognitive space to follow rules better
- reference-docs - On-demand knowledge loaded only when needed for current task
- knowledge-composition - Split knowledge into focused, composable files with single responsibilities
- semantic-zoom - Control abstraction levels—zoom out for overview or zoom in for details
- noise-cancellation - Explicitly ask AI to be succinct and strip filler from responses
Reliability & Quality
Handling non-determinism, complexity, and verification.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 133 lines · 40 tokens per session scan A 20b409e4574a
ai-patterns is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 8d ago), licensed Unlicense. It adds 40 tokens to every session and 1,263 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ai-patterns, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log to draft the six root pages and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the brain CLI. Run it after brain-setup.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
harness-design
Design and build multi-agent harness architectures for long-running AI application development. GAN-inspired Generator-Evaluator pattern, Sprint Contract negotiation, context management, quality criteria calibration. Based on Anthropic Engineering patterns. Use when: "build a harness", "multi-agent architecture"…
verify-this
Prove a concrete behavior, performance, UI, CLI, API, or memory claim with fresh baseline-versus-treatment evidence and one explicit verdict. Use when asked to verify, prove, compare before and after, show evidence, or confirm that a fix works. Do not use for vague claims such as cleaner code, a full plan-based…
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code SessionStart hook.