What is frustration-hunter?

A user-frustration analysis guide that finds and ranks signals such as repeated clicks, unresponsive clicks, abandoned forms, and error spikes.

Use it to find the biggest frustrations on a site, investigate a page or flow, compare changes over time, and inspect affected sessions.

It helps identify the user-experience problems affecting the most people and supports the findings with session evidence.

frustration-hunter — Skill for Claude Code by reatlat

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 frustration-hunter

Clone the repo

git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-reatlat, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/frustration-hunter/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/frustration-hunter)

Your own site

<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/frustration-hunter"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/frustration-hunter/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/frustration-hunter"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/frustration-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,016 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.01016
Opus 5.5	$0.00027	$0.00406
Sonnet 5.5	$0.00013	$0.00203
Haiku 4.5	$0.00007	$0.00102

Measured 7d ago against content hash 8734f1d6c94f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frustration-hunter 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/frustration-hunter/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frustration Hunter

Find what's frustrating your users, ranked by impact, grounded in real session evidence.

When to Use

"What are the biggest frustrations on our site right now?"
"What's causing friction on the checkout flow for mobile users?"
"What got worse this week vs last week?"
"Show me the top rage-clicked elements across our product"
"Find sessions where users are dead-clicking on the settings page"

Use free fullstory:discover_groups and fullstory:get_opportunity_stats for live signals. Discovery accepts one scope at a time (page_id, domain, app_name, segment_id, or funnel_id); use a segment for device/user filters and the live schema for time ranges. Use computed metrics for exact custom windows.

Workflow

Step 1: Discover opportunities

Call fullstory:discover_groups for the requested window (default last 7 days, using the live schema). This returns the top live frustration signals — rage clicks, dead clicks, form abandonment, error spikes — each with a user count and page location.

If the user asks about a specific page or flow, scope the opportunities to that area. If they ask "what got worse," set compare_to_previous=true.

Step 2: Get live stats

For the top 3-5 opportunities, call fullstory:get_opportunity_stats on each. This returns:

Exact user count (not an estimate)
Device split (mobile vs desktop percentage)
Page concentration (which pages it happens on)
Rate-of-change vs prior period (is it getting worse?)
Frustration rate vs site average

Present the top frustrations as a ranked list:

1. Rage clicks on "Apply Promo Code" — 412 users, 73% mobile, /checkout
2. Dead clicks on cart icon — 287 users, Safari-specific, /products
3. Form abandonment at password field — 218 users, 22s avg dwell before leaving

Step 3: Pull sessions for the worst offenders

For the top 1-3 signals, build a metric describing the observed frustration, compute it, and call fullstory:get_sessions(metric_id="<id>"). Review 3-5 returned sessions per signal.

Read the full file on GitHub · 80 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.

7d ago Changed · +4 lines 8734f1d6c94f
2mo ago First seen · 76 lines · 67 tokens per session scan A 9d0aa167df55

Subscribe to this mod's changes

frustration-hunter is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (35 stars, last pushed 7d ago), licensed MIT. It adds 67 tokens to every session and 1,016 once invoked, about $0.0003 per session on Opus 5.5. 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.

Analytics and metrics Claude Code Design and UX ai-skills claude claude-plugin cursor

frustration-hunter next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
frustration-hunterreatlat/fullstory-claude-plugin	Skill	35	7d ago	MIT	A	67	Claude Code
roblox-guiTabooHarmony/roblox-brain	Skill	162	23d ago	MIT	A	34	Claude Code
bitrix-uibxmaximum/bitrix-framework-skills	Skill	52	2d ago	MIT	A	57	Claude Code, Codex
ref-auditp4inz-code/3d-ref-skills	Skill	14	yesterday	MIT	A	128	Claude Code, Codex
ref-style-decodep4inz-code/3d-ref-skills	Skill	14	yesterday	MIT	A	72	Claude Code, Codex
form-croborghei/Claude-Skills	Skill	1.1k	14d ago	none	A	43	Claude Code
page-croborghei/Claude-Skills	Skill	1.1k	14d ago	none	A	39	Claude Code