revenue-impact

revenue-impact is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 33 tokens per session (696 once invoked), scanned A, original, MIT.

A method for choosing which language model an agent should use for each task. It checks settings in a defined order, including per-agent and global project configuration.

In plain words
What is it for?
Use it to determine the model for an agent, save model preferences in .squad/config.json, and include the selected model when starting agent tasks.
Why use it?
Projects may have several model preferences that conflict or apply at different levels. This resolves them consistently so each agent receives a clear model choice.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: positional $N argument.

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

Good fit Use it to determine the model for an agent, save model preferences in .squad/config.json, and include the selected model when starting agent tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/revenue-impact
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 revenue-impact
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 revenue-impact

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/revenue-impact"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/revenue-impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 696 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 $0.00033 $0.00696
Opus 5 $0.00016 $0.00348
Sonnet 5 $0.00007 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured 12d ago against content hash 1f36cb970eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

revenue-impact 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 12d 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/revenue-impact/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revenue Impact

Estimate the revenue cost of UX issues — put a dollar figure on rage clicks, conversion drops, and error spikes.

When This Runs

Invoked automatically by frustration-hunter, funnel-doctor, and error-forensics when the user asks "what does this cost us?" or "what's the revenue impact?" Not user-invocable directly.

Workflow

Step 1: Get the affected user count

From whichever skill invoked this, extract:

  • How many users are affected (from get_opportunity_stats or compute_metric)
  • Over what time period

Step 2: Get the business numbers

Ask the user for:

  • Average order value (AOV) or average revenue per user
  • Conversion rate for the affected flow (if not already known)
  • Traffic volume to the affected page (if not already known)

If they don't know, offer to compute from Fullstory:

fullstory:build_metric(query="completed purchases", output_type="single_number")
fullstory:compute_metric(metric_id)
→ also compute total unique users on the checkout page
→ derive: conversion rate = completed / total

For AOV: Fullstory doesn't track revenue natively (unless it's sent as a custom event). If revenue data isn't in Fullstory, ask the user for AOV. Don't guess.

Step 3: Calculate

Basic formula:

Revenue lost = affected users × conversion rate × AOV

Example:

  • 412 users rage-clicked "Apply Promo" on checkout
  • Checkout conversion rate: 20%
  • AOV: $85

"Of those 412 users, if the rage click caused even half of them to abandon — that's potentially 41 lost purchases (412 × 20% × 50% abandon rate). At $85 AOV, that's ~$3,500 in the last 7 days, or $182K annualized."

Be explicit about assumptions. Use ranges: "$3,000–5,000" not "$3,472."

Step 4: Present with context

Always show:

  1. The UX issue (what's broken)
  2. User impact (how many affected)
  3. Revenue estimate (with assumptions stated)
  4. Time period (per week, per month, annualized)
  5. Confidence level (high if you have session evidence, low if you're extrapolating from small samples)

Read the full file on GitHub · 72 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. 12d ago First seen · 72 lines · 33 tokens per session scan A 1f36cb970eb4

Subscribe to this mod's changes

revenue-impact is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 696 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.