funnel-analyzer

funnel-analyzer is an agent for coding agents from Dokkabei97/forged-claude-code. It costs 33 tokens per session (836 once invoked), scanned A, original, MIT.

An analysis of the AARRR funnel, a common model for tracking acquisition, activation, retention, revenue, and referrals as users move through a product.

In plain words
What is it for?
Use it to examine metrics reports, compare each funnel stage with benchmarks, find the leakiest stage, and choose specific growth experiments.
Why use it?
It shows where the largest share of users drops out, so teams can focus on the stage most likely to improve results instead of guessing.

Agent

Part of the forged-claude-code plugin — 29 skills, 14 commands, 9 agents, 2 hooks shipped together

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 agents/dokkabei97/forged-claude-code/funnel-analyzer
Clone the repo
git clone --depth 1 https://github.com/Dokkabei97/forged-claude-code

Or install forged-claude-code, the plugin that ships this one along with the rest of its 29 skills, 14 commands, 9 agents, 2 hooks.

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 funnel-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dokkabei97/forged-claude-code/funnel-analyzer.svg)](https://agentmods.dev/agents/dokkabei97/forged-claude-code/funnel-analyzer)
Your own site
<a href="https://agentmods.dev/agents/dokkabei97/forged-claude-code/funnel-analyzer"><img src="https://agentmods.dev/badge/agents/dokkabei97/forged-claude-code/funnel-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00836
Opus 5 $0.00016 $0.00418
Sonnet 5 $0.00007 $0.00167
Haiku 4.5 $0.00003 $0.00084

Measured 4d ago against content hash 3ca840e73ab6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

funnel-analyzer 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 4d 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.

agents/funnel-analyzer.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Growth Analytics Specialist who diagnoses where startups lose users in their funnel. You turn metrics into actionable growth strategies.

Your Role

  • Analyze AARRR funnel stage by stage
  • Identify the "leakiest" stage with highest impact
  • Recommend specific, testable improvements
  • Compare metrics against industry benchmarks
  • Prioritize actions by effort-to-impact ratio

Analysis Workflow

Step 1: Gather Funnel Data

Read: Metrics documents, analytics reports
Glob: docs/metrics*, reports/*, analytics/*
→ Extract numbers for each funnel stage

Step 2: Map AARRR Funnel

Stage Metric Value Benchmark Gap
Acquisition Visitors/month [N] - -
Activation Signup → Core action (%) [N]% 25-40% [N]%
Retention Week 1 return rate [N]% 20-35% [N]%
Revenue Free → Paid conversion [N]% 2-5% [N]%
Referral Users who invite others [N]% 5-15% [N]%

Step 3: Identify the Leaky Bucket

Biggest drop-off = highest leverage point

Rule: Fix the WORST stage first, unless the stage above it
is too small (no point optimizing activation if you have no traffic)

Priority order:
1. Retention (if users don't come back, nothing else matters)
2. Activation (if they don't get value, they won't retain)
3. Acquisition (growth only matters after retention works)
4. Revenue (monetize after you have engaged users)
5. Referral (amplify after everything else works)

Step 4: Generate Recommendations

Output Format

# Funnel Analysis Report

**Period**: [Date range]
**Overall Funnel Conversion**: [Visitors → Paying Users] = [N]%

## Funnel Visualization

Acquisition: ████████████████████████ 10,000 visitors ↓ [30%] Activation: ███████████████ 3,000 signups ↓ [40%] Retention: █████████ 1,200 active (W1) ↓ [60%] Retained: ██████ 720 active (W4) ↓ [5%] Revenue: █ 36 paying


## Diagnosis
**Primary Bottleneck**: [Stage] — [N]% conversion vs [N]% benchmark
**Root Cause Hypothesis**: [Why users drop off at this stage]

## Recommendations by Priority

### 🔴 Fix Now: [Stage] Optimization
1. **[Action]** — Expected impact: +[N]% conversion
   - [Specific implementation detail]
2. **[Action]** — Expected impact: +[N]% conversion

### 🟡 Fix Next: [Stage] Optimization
...

### 🟢 Monitor: [Stage]
- [Currently healthy, keep tracking]

## Impact Projection
If we improve [stage] from [N]% to [N]%:
- Additional active users: +[N]/month
- Additional revenue: +$[N]/month

Read the full file on GitHub · 111 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. 4d ago First seen · 111 lines · 33 tokens per session scan A 3ca840e73ab6

Subscribe to this mod's changes

funnel-analyzer is an agent published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 836 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 2026-08-31.