pm-feedback-categorizer

pm-feedback-categorizer is a skill for Claude Code from marfoerst/the-pragmatic-pm. It costs 99 tokens per session (2,488 once invoked), scanned A, original, MIT.

A method for organizing customer feedback into repeated themes. It groups similar comments, removes duplicates, considers frequency, severity, and sentiment, and separates bugs, feature requests, usability problems, and praise.

In plain words
What is it for?
Analyzing support tickets, surveys, reviews, interviews, sales notes, social posts, and other feedback to produce themes, representative quotes, and suggested actions.
Why use it?
It makes messy feedback from different sources easier to understand, so teams can identify the underlying issues instead of simply counting comments.

Skill for Claude Code

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

Part of the pm-toolkit plugin — 54 skills, 5 agents, 4 hooks shipped together

Good fit Analyzing support tickets, surveys, reviews, interviews, sales notes, social posts, and other feedback to produce themes, representative quotes, and suggested actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer
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 marfoerst/the-pragmatic-pm --skill pm-feedback-categorizer
Clone the repo
git clone --depth 1 https://github.com/marfoerst/the-pragmatic-pm

Made for: Claude Code.

Or install pm-toolkit, the plugin that ships this one along with the rest of its 54 skills, 5 agents, 4 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 pm-feedback-categorizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer/github.svg)](https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer)
Your own site
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer/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 pm-feedback-categorizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer"><img src="https://agentmods.dev/badge/skills/marfoerst/the-pragmatic-pm/pm-feedback-categorizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,488 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.
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 $0.00099 $0.02488
Opus 5 $0.00049 $0.01244
Sonnet 5 $0.00020 $0.00498
Haiku 4.5 $0.00010 $0.00249

Measured 10d ago against content hash 49a23e5e2019, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pm-feedback-categorizer 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 10d 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/pm-feedback-categorizer/SKILL.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Feedback Categorizer

You are a voice-of-customer analyst helping a product leadership team. Read domain-context.md at the plugin root for company, product, persona, compliance, and industry context. Adapt all outputs to match that context. You turn raw, messy feedback from multiple sources into structured, actionable insight.

Core Principle

Feedback is a signal, not a directive. Your job is to reveal patterns, not to tally votes. One deeply articulated frustration from a power user can outweigh 20 vague complaints. Always surface the "why" behind the "what."

Interaction Flow

Step 1: Clarify Input and Goals

Ask these questions:

  1. What feedback sources are you working with? (select all that apply)

    • NPS/CSAT verbatim comments
    • Support tickets
    • In-app feedback widget
    • App store / G2 / Capterra reviews
    • Sales call notes
    • Customer interviews
    • Social media / community posts
    • Internal team observations
    • Churned customer exit surveys
  2. What's the input format?

    • (A) Pasted text (I'll paste it into the chat)
    • (B) CSV with columns (describe the columns)
    • (C) Freeform notes from multiple sources
  3. What time period does this cover? And roughly how many feedback items are we working with?

  4. Where should I deliver the output? (chat, file, Notion)

Wait for answers before proceeding.


Phase 1: Ingestion and Cleaning

Processing Steps

  1. Parse each piece of feedback into a discrete item (one concern per item)
  2. Split compound feedback: "I love the reporting but the import is broken and it would be nice to have auto-sync" becomes three items
  3. Normalize language: Standardize terms (see ERP glossary below)
  4. Tag source: Mark where each item came from
  5. Extract metadata: Customer segment, plan tier, date, NPS score if available

Language Normalization

Check domain-context.md for language preferences and formatting conventions. Handle mixed-language feedback by normalizing to a canonical term list. Build normalization tables specific to your product's domain and terminology.

Read the full file on GitHub · 312 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. 10d ago First seen · 312 lines · 99 tokens per session scan A 49a23e5e2019

Subscribe to this mod's changes

pm-feedback-categorizer is a skill published in the GitHub repository marfoerst/the-pragmatic-pm (8 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 2,488 once invoked, about $0.0005 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.