nps-proxy

nps-proxy is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 47 tokens per session (1,541 once invoked), scanned A, original, MIT.

A way to estimate user satisfaction from behavior in Fullstory, a service that records website and app sessions, instead of asking users a survey question. It uses success, frustration, and engagement signals as an indirect measure.

In plain words
What is it for?
Use it to track behavior-based satisfaction trends, compare changes after a redesign, and identify users showing promoter-like or detractor-like behavior.
Why use it?
It provides a directional satisfaction signal when you do not have Net Promoter Score (NPS) survey responses. It is not a replacement for asking users directly.

Skill for Claude Code

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

Part of the fullstory-claude-plugin plugin — 46 skills, 3 agents, 1 MCP server shipped together

Good fit Use it to track behavior-based satisfaction trends, compare changes after a redesign, and identify users showing promoter-like or detractor-like behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/nps-proxy
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 reatlat/fullstory-claude-plugin --skill nps-proxy
Clone the repo
git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-claude-plugin, the plugin that ships this one along with the rest of its 46 skills, 3 agents, 1 MCP server.

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 nps-proxy

README.md
[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/nps-proxy/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/nps-proxy)
Your own site
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/nps-proxy"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/nps-proxy/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 nps-proxy

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/nps-proxy"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/nps-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,541 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00047 $0.01541
Opus 5 $0.00023 $0.00771
Sonnet 5 $0.00009 $0.00308
Haiku 4.5 $0.00005 $0.00154

Measured 9d ago against content hash 6d1f17ca0df0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nps-proxy 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 9d 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/nps-proxy/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NPS Proxy

Measure user satisfaction from behavior when you don't have survey data — frustration signals, engagement patterns, and conversion behavior as a real-time proxy for how users feel.

When to Use

  • "What's our user satisfaction looking like?"
  • "We don't run NPS surveys — can Fullstory give us a satisfaction signal?"
  • "Which users are likely promoters vs detractors based on behavior?"
  • "Did satisfaction improve after the redesign?"
  • "Show me our 'frustration score' trend over time"

Mental Model

NPS (Net Promoter Score) asks users: "How likely are you to recommend us?" Fullstory doesn't do surveys. But you can build a behavioral proxy from three signals:

  1. Success signals (promoters): Completed key tasks, returned multiple times, used advanced features, high engagement
  2. Frustration signals (detractors): Rage clicks, dead clicks, errors, form abandonment, one-and-done sessions
  3. Engagement signals (passives): Consistent but shallow usage, moderate session frequency, no strong positive or negative signals

The ratio of success to frustration signals gives you a directional satisfaction measure. It's not a survey. It's a behavioral proxy. Treat it accordingly.

Workflow

Step 1: Define success and frustration signals

Work with the user to define what "happy" and "unhappy" look like in their product:

Success signals (any 2+ = likely satisfied):

  • Completed a purchase, signup, or key conversion
  • Used the product 3+ times in 30 days
  • Session duration >5 minutes (engaged, not bouncing)
  • Used advanced features (beyond basics)
  • Returned after first session (retained)
  • No frustration events in any session

Frustration signals (any 1 = likely unsatisfied):

  • Rage clicked any element
  • Dead clicked any element
  • Hit a console error or network failure
  • Abandoned a form mid-completion
  • Bounced after 1 page view (<10 seconds)
  • Visited help/support pages repeatedly

Step 2: Build satisfaction segments

fullstory:build_segment("users with at least 2 success signals and 0 frustration signals in last 30 days") → promoters
fullstory:build_segment("users with at least 1 frustration signal in last 30 days") → detractors
fullstory:build_segment("users with neither strong success nor frustration signals in last 30 days") → passives

Read the full file on GitHub · 149 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. 9d ago First seen · 149 lines · 47 tokens per session scan A 6d1f17ca0df0

Subscribe to this mod's changes

nps-proxy is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 27d ago), licensed MIT. It adds 47 tokens to every session and 1,541 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 2026-08-30.