ai-product

ai-product is a skill for Claude Code, Codex from bugrabilge/bilge-development-kit. It costs 43 tokens per session (467 once invoked), scanned A, a copy of ai-product, MIT.

A guide to building products that use large language models—AI systems that generate and understand text. It covers output checks, prompt versioning, streaming responses, and safety issues when moving from a demo to a real product.

In plain words
What is it for?
Use it to design LLM features, structure and validate model outputs, test prompt changes, stream responses, sanitize user input, and add production safety checks.
Why use it?
It helps reduce unreliable answers, unsafe handling of user input, inconsistent formats, high costs, and failures caused by sending too much context to a model.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/bugrabilge/bilge-development-kit/ai-product
Any agent
npx skills add bugrabilge/bilge-development-kit --skill ai-product
Clone the repo
git clone --depth 1 https://github.com/bugrabilge/bilge-development-kit

Made for: Claude Code, Codex.

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-product

README.md
[![agentmods](https://agentmods.dev/badge/skills/bugrabilge/bilge-development-kit/ai-product.svg)](https://agentmods.dev/skills/bugrabilge/bilge-development-kit/ai-product)
Your own site
<a href="https://agentmods.dev/skills/bugrabilge/bilge-development-kit/ai-product"><img src="https://agentmods.dev/badge/skills/bugrabilge/bilge-development-kit/ai-product.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00043 $0.00467
Opus 5 $0.00022 $0.00234
Sonnet 5 $0.00009 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured 5d ago against content hash 498cc0f3f0e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ai-product 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 5d 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.

Origin

This is a copy

88% identical to ai-product — 6 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.

skills-extra/ai-product/SKILL.md · 59 lines

What it actually says

AI Product Development

You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard. You treat prompts as code, validate all outputs, and never trust an LLM blindly.

Patterns

Structured Output with Validation

Use function calling or JSON mode with schema validation

Streaming with Progress

Stream LLM responses to show progress and reduce perceived latency

Prompt Versioning and Testing

Version prompts in code and test with regression suite

Anti-Patterns

❌ Demo-ware

Why bad: Demos deceive. Production reveals truth. Users lose trust fast.

❌ Context window stuffing

Why bad: Expensive, slow, hits limits. Dilutes relevant context with noise.

❌ Unstructured output parsing

Why bad: Breaks randomly. Inconsistent formats. Injection risks.

⚠️ Sharp Edges

Issue Severity Solution
Trusting LLM output without validation critical # Always validate output:
User input directly in prompts without sanitization critical # Defense layers:
Stuffing too much into context window high # Calculate tokens before sending:
Waiting for complete response before showing anything high # Stream responses:
Not monitoring LLM API costs high # Track per-request:
App breaks when LLM API fails high # Defense in depth:
Not validating facts from LLM responses critical # For factual claims:
Making LLM calls in synchronous request handlers high # Async patterns:

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

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. 5d ago First seen · 59 lines · 43 tokens per session scan A 498cc0f3f0e8

Subscribe to this mod's changes

ai-product is a skill published in the GitHub repository bugrabilge/bilge-development-kit (10 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 467 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to ai-product, differing in 6 lines, and is treated as a copy.