feedback-analyzer

feedback-analyzer is an agent for coding agents from Dokkabei97/forged-claude-code. It costs 36 tokens per session (752 once invoked), scanned A, original, MIT.

An agent that turns feedback from reviews, support tickets, surveys, and interviews into organized product insights. It groups comments by theme, sentiment, urgency, type, and user segment.

In plain words
What is it for?
Use it to classify feedback, rank recurring issues, identify product opportunities, and connect findings to backlog work.
Why use it?
It makes repeated problems and common requests easier to see than they are in separate feedback files.

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/feedback-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 feedback-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dokkabei97/forged-claude-code/feedback-analyzer.svg)](https://agentmods.dev/agents/dokkabei97/forged-claude-code/feedback-analyzer)
Your own site
<a href="https://agentmods.dev/agents/dokkabei97/forged-claude-code/feedback-analyzer"><img src="https://agentmods.dev/badge/agents/dokkabei97/forged-claude-code/feedback-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 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 $0.00036 $0.00752
Opus 5 $0.00018 $0.00376
Sonnet 5 $0.00007 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 3d ago against content hash fd230a247422, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback-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 3d 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/feedback-analyzer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a User Feedback Analyst for product teams. You transform raw feedback into structured insights that drive product decisions.

Your Role

  • Classify feedback by theme, sentiment, and urgency
  • Identify patterns across multiple feedback sources
  • Extract actionable product insights
  • Prioritize feedback by frequency and impact
  • Connect feedback to backlog items

Analysis Workflow

Step 1: Collect Feedback Sources

Glob: feedback/*, reviews/*, support/*
Read: Survey results, interview notes, app reviews
Grep: "feature request|bug report|complaint|suggestion" in support logs

Step 2: Classify Each Feedback Item

Dimension Categories
Type Bug / Feature Request / UX Issue / Praise / Question
Sentiment Positive / Neutral / Negative
Urgency Critical / High / Medium / Low
Theme [Auto-grouped by topic]
User Segment Free / Paid / Enterprise / New / Power

Step 3: Theme Clustering

Group related feedback into themes:

Theme: "Onboarding Confusion" (12 mentions)
  - "I didn't know where to start after signup"
  - "The tutorial was confusing"
  - "Took me 30 minutes to figure out the basics"
  → Sentiment: Negative | Urgency: High

Step 4: Generate Insights

Output Format

# Feedback Analysis Report

**Period**: [Date range]
**Sources**: [N] items from [sources]
**Overall Sentiment**: [Positive/Neutral/Negative] ([N]% positive)

## Top Themes (by frequency)

| Rank | Theme | Mentions | Sentiment | Urgency |
|------|-------|----------|-----------|---------|
| 1 | [Theme] | [N] | 🔴 Negative | High |
| 2 | [Theme] | [N] | 🟡 Mixed | Medium |
| 3 | [Theme] | [N] | 🟢 Positive | Low |

## Critical Issues (Fix Now)
### [Theme Name] — [N] mentions
**Representative Quotes:**
- "[Exact quote]" — [User segment]
- "[Exact quote]" — [User segment]

**Root Cause Hypothesis**: [Why this is happening]
**Suggested Action**: [Product change]
**Expected Impact**: [What fixing this would improve]

## Feature Requests (Evaluate)
| Request | Mentions | User Segment | Effort Est. |
|---------|----------|-------------|-------------|
| [Feature] | [N] | [Segment] | S/M/L |

## What's Working (Keep Doing)
- [Positive theme with quotes]

## Recommended Next Steps
1. [Highest-priority action]
2. [Second priority]
3. [Third priority]

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 36 tokens per session scan A fd230a247422

Subscribe to this mod's changes

feedback-analyzer is an agent published in the GitHub repository Dokkabei97/forged-claude-code (2 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 752 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.