ai-llm-engineering

ai-llm-engineering is a skill for Claude Code from soden46/engineer-flow. It costs 31 tokens per session (314 once invoked), scanned A, original, MIT.

A set of engineering guidelines for building and running systems that use large language models, which generate text or other outputs from instructions. It covers integrations, agents, prompts, embeddings, search-based retrieval, evaluation, and AI pipelines.

In plain words
What is it for?
Use it to design or review LLM features, validate tool inputs and permissions, define structured outputs, evaluate models with representative tests, and manage latency, cost, retries, limits, and fallbacks.
Why use it?
It treats model output as uncertain and helps separate model instructions from application logic, tools, stored data, and testing. This reduces risks such as unsafe tool actions, poor retrieval, and untested changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the engineer-flow plugin — 18 skills shipped together

Good fit Use it to design or review LLM features, validate tool inputs and permissions, define structured outputs, evaluate models with representative tests, and manage latency, cost, retries, limits, and fallbacks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soden46/engineer-flow/ai-llm-engineering
Install

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.

Any agent
npx skills add soden46/engineer-flow --skill ai-llm-engineering
Clone the repo
git clone --depth 1 https://github.com/soden46/engineer-flow

Made for: Claude Code.

Or install engineer-flow, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for ai-llm-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/soden46/engineer-flow/ai-llm-engineering.svg)](https://agentmods.dev/skills/soden46/engineer-flow/ai-llm-engineering)
Your own site
<a href="https://agentmods.dev/skills/soden46/engineer-flow/ai-llm-engineering"><img src="https://agentmods.dev/badge/skills/soden46/engineer-flow/ai-llm-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00314
Opus 5 $0.00015 $0.00157
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00031

Measured 7d ago against content hash d483ed9a69ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ai-llm-engineering 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 7d 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.

skills/engineer-flow/core/ai-llm-engineering/SKILL.md · 65 lines

What it actually says

ai-llm-engineering

Use this skill for LLM integrations, agents, prompts, embeddings, retrieval, evaluation, model workflows, and AI pipelines.

Principles

Treat model output as untrusted and nondeterministic.

Separate:

  • model instructions
  • application logic
  • tools
  • retrieval
  • persistence
  • evaluation

Define expected outputs and failure behavior.

For structured output use enforceable schemas where available.

For tool use:

  • validate arguments
  • enforce authorization outside the model
  • limit tool capability
  • verify side effects

For retrieval systems evaluate both retrieval quality and final answer quality.

For prompts:

  • state the task clearly
  • provide relevant context
  • avoid irrelevant context
  • define output constraints where useful

For evaluation use representative cases and frozen test sets when comparing changes.

Do not tune against held-out evaluation cases.

For expensive model workloads consider:

  • latency
  • token usage
  • caching
  • batching
  • retries
  • rate limits
  • fallback behavior

Do not treat model confidence as proof of correctness.

Adaptation

Use project evidence to determine the actual language, framework, runtime, and existing conventions.

When stack-specific implementation guidance is needed, prefer project evidence, native framework or language mechanisms, and relevant user-installed specialist skills. Technology-specific guidance must not redefine or weaken the core engineering requirement.

Changes

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.

  1. 7d ago First seen · 65 lines · 31 tokens per session scan A d483ed9a69ae

Subscribe to this mod's changes

ai-llm-engineering is a skill published in the GitHub repository soden46/engineer-flow (3 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 314 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

promptly-prompt

Clarity gate for prompts: intercepts unclear requests and forces the model to restate the user's intent to align before working, then diagnose the root cause and reuse the domain's mature, established practices before improvising. Clear prompts pass through untouched.

ViryaZheng/promptly-prompt · 59 tokens

hunt-llm-ai

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use, ASCII smuggling, agentic AI security framework (ASI01-ASI10). Patterns: direct prompt injection in user input (bypass system prompt with 'ignore previous instructions'), indirect injection via documents/web pages the model…

adriannoes/awesome-agentic-ai · 226 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

sinhoneyy/master-skills · 41 tokens

implementing-llm-guardrails-for-security

Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…

adriannoes/awesome-agentic-ai · 143 tokens

ai-prompt-writing

Write effective prompts for AI coding tools — structure task context, specify constraints, provide examples, and iterate based on output quality. Targets developers using Claude Code, Copilot, Cursor, and similar tools.

The-AI-Directory-Company/agents-and-skills · 45 tokens

prompt-engineering-guide

Design, test, and optimize LLM prompts systematically — with evaluation frameworks, chain-of-thought patterns, output formatting, and iteration methodology for reliable AI outputs.

The-AI-Directory-Company/agents-and-skills · 37 tokens