ai-feature-validation

ai-feature-validation is a skill for Claude Code from RBraga01/builder-product. It costs 53 tokens per session (1,857 once invoked), scanned A, original, MIT.

A review process for user-facing features that use artificial intelligence, such as language models. It checks how the product handles wrong answers, user trust, expanding scope, and actions that cannot easily be undone.

In plain words
What is it for?
Use it when approving, expanding, or reviewing an AI feature, especially one that shows generated text, predictions, or decisions to users.
Why use it?
Regular feature reviews may miss problems caused by AI output changing or being incorrect. This process makes those risks part of the approval decision before development begins.

Skill for Claude Code

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

Part of the builder-product plugin — 7 skills, 3 agents shipped together

Good fit Use it when approving, expanding, or reviewing an AI feature, especially one that shows generated text, predictions, or decisions to users.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rbraga01/builder-product/ai-feature-validation
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 RBraga01/builder-product --skill ai-feature-validation
Clone the repo
git clone --depth 1 https://github.com/RBraga01/builder-product

Made for: Claude Code.

Or install builder-product, the plugin that ships this one along with the rest of its 7 skills, 3 agents.

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-feature-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbraga01/builder-product/ai-feature-validation/github.svg)](https://agentmods.dev/skills/rbraga01/builder-product/ai-feature-validation)
Your own site
<a href="https://agentmods.dev/skills/rbraga01/builder-product/ai-feature-validation"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-product/ai-feature-validation/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.

agentmods 80×15 button for ai-feature-validation

Your own site · 80×15
<a href="https://agentmods.dev/skills/rbraga01/builder-product/ai-feature-validation"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-product/ai-feature-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,857 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 $0.00053 $0.01857
Opus 5 $0.00026 $0.00928
Sonnet 5 $0.00011 $0.00371
Haiku 4.5 $0.00005 $0.00186

Measured 8d ago against content hash e2c55481bfc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-feature-validation 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.

skills/ai-feature-validation/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Feature Validation

The Law

AI FEATURES HAVE FAILURE MODES THAT DETERMINISTIC FEATURES DO NOT.
"We validated it like any other feature" misses hallucination UX, trust calibration, scope creep, and irreversibility — none of which appear in a standard acceptance criterion.
All four AI-specific risks addressed in the PRD IS AI feature validation.

When to Use

Trigger before:

  • Approving any AI feature for development
  • Adding an LLM call to any user-facing surface
  • Expanding an existing AI feature's scope or capability
  • Reviewing a PRD that includes AI-generated content, predictions, or decisions

When NOT to Use

  • Backend AI pipelines with no user-visible output (use ai-safety-review from builder-ai instead)
  • Features where the model output is filtered through deterministic rules before reaching users (the rules are the product; validate the rules)

The Four AI-Specific Risks

Standard PRD review asks: does the feature solve the user problem? AI feature validation asks four additional questions that standard PRDs never reach.

Risk 1 — Hallucination UX

What does the product look like when the model is wrong?

Every AI feature produces incorrect outputs. The question is not "will it hallucinate?" but "what does the UX do when it does?"

Required answers in the PRD:

  • What is the worst plausible incorrect output for this feature? (e.g., "a medical dosage that is wrong by an order of magnitude")
  • What does the user see when the model is wrong? Is it distinguishable from a correct output?
  • Is there a confidence signal that alerts users to lower-confidence outputs?
  • Is there a correction mechanism — can the user flag, override, or report an incorrect output?
  • For high-stakes domains: is there an explicit disclaimer at the point of use?

BLOCK if:

  • Incorrect outputs are visually identical to correct outputs with no uncertainty signal
  • There is no correction mechanism for high-stakes outputs (medical, legal, financial, safety)

Read the full file on GitHub · 173 lines

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. 8d ago First seen · 173 lines · 0 tokens per session scan A e2c55481bfc5

Subscribe to this mod's changes

ai-feature-validation is a skill published in the GitHub repository RBraga01/builder-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,857 once invoked, about $0.0003 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

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

prompt-master

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…

nidhinjs/prompt-master · 78 tokens

flux2-lora-training

Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.

AnastasiyaW/codex-claude-code-config · 73 tokens

vlm-segmentation

Choose and evaluate VLM or segmentation pipelines, including text-conditioned detection, masks, part labels, model-license constraints, and measured GPU deployment choices. Use when a task has a VLM or segmentation component; route pure diffusion prompting, training, or serving to its specialized skill.

AnastasiyaW/codex-claude-code-config · 61 tokens

deepseek-provider-contract

Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries. Use when integrating DeepSeek, adding DeepSeek tool calls or streaming, debugging DeepSeek 400 after a tool call, or…

AnastasiyaW/codex-claude-code-config · 98 tokens

forensic-prompt-compiler

Forensic image-to-prompt compiler for image generation models. Use this skill whenever the user wants to: convert/describe an existing image into a generation prompt, reconstruct a scene as a prompt, generate prompts from reference images for AI image tools (Midjourney, FLUX, Stable Diffusion, DALL-E, or any diffusion…

AnastasiyaW/codex-claude-code-config · 218 tokens