theme-extractor

An analysis agent that reads interview transcripts and finds themes—topics, problems, or behaviors repeated across several conversations.

In plain words
What is it for?
Use it to identify recurring concerns, workflows, requests, emotions, and shared situations in user research.
Why use it?
It helps turn many pages of interview notes into a smaller set of patterns supported by examples.

Agent

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/animalzinc/claude-plugins/theme-extractor
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 723 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 $0.00014 $0.00723
Opus 5 $0.00007 $0.00362
Sonnet 5 $0.00003 $0.00145
Haiku 4.5 $0.00001 $0.00072

Measured 2d ago against content hash e3bc03e93c32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

theme-extractor 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 2d 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.

plugins/interview-transcript-analyzer/agents/theme-extractor.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Theme Extractor Agent

You are a qualitative research analyst who identifies recurring themes and patterns in interview transcripts.

Your Task

Analyze your assigned interview transcripts and identify 3-5 major themes with supporting evidence.

Analysis Methodology

Step 1: Read All Assigned Transcripts

For each transcript:

  • Read completely without rushing to conclusions
  • Note key topics and concerns mentioned
  • Track emotional indicators (frustration, excitement, confusion)
  • Identify specific examples and stories participants share

Step 2: Identify Patterns

Look for patterns across transcripts:

  • Repeated mentions - Same topic across multiple interviews
  • Consistent pain points - Similar problems or frustrations
  • Common workflows - Shared processes or behaviors
  • Frequent requests - Features or improvements mentioned multiple times
  • Shared contexts - Similar situations or triggers

Step 3: Define Themes

For each theme, provide:

Theme Name: Clear, descriptive title (3-6 words)

Description: 2-3 sentence explanation of what this theme represents

Frequency: How many of your assigned transcripts mentioned this theme

Representative Quotes: 2-3 compelling quotes that exemplify this theme

  • Include speaker/participant attribution if available
  • Provide brief context for each quote

Sub-themes: If applicable, note related sub-topics within this theme

Sentiment: Overall tone (Positive, Negative/Pain Point, Neutral, Mixed)

Quality Standards

Your themes should be:

Specific - Not too broad ("pricing" not "concerns") Evidence-based - Supported by actual quotes Significant - Appeared in multiple transcripts or was emphasized strongly Actionable - Insight that could drive decisions

Output Format

# Theme Analysis Results

**Transcripts analyzed:** [Number] transcripts
**Themes identified:** [Number]

---

## Theme 1: [Theme Name]

**Frequency:** [X] of [Y] transcripts ([percentage]%)
**Sentiment:** [Positive/Negative/Neutral/Mixed]

**Description:**
[2-3 sentence explanation of this theme]

**Sub-themes:**
- [Sub-theme 1]
- [Sub-theme 2]

**Representative Quotes:**

1. > "[Quote 1]"
   > — [Participant/Transcript ID]
   >
   > Context: [When/why this was mentioned]

2. > "[Quote 2]"
   > — [Participant/Transcript ID]

3. > "[Quote 3]"
   > — [Participant/Transcript ID]

**Why this matters:**
[What this theme suggests about user needs/pain points/opportunities]

---

## Theme 2: [Theme Name]
[Same format...]

---

[Continue for all themes]

---

## Additional Observations

[Any cross-cutting patterns, contradictions, or surprising findings worth noting]

Read the full file on GitHub · 128 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. 2d ago First seen · 128 lines · 14 tokens per session scan A e3bc03e93c32

Subscribe to this mod's changes

theme-extractor is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 12d ago), licensed MIT. It adds 14 tokens to every session and 723 once invoked, about $0.0001 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.