Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/animalzinc/claude-pluginsnpx agentmods add commands/animalzinc/claude-plugins/extract-quotesWrote 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.
[](https://agentmods.dev/commands/animalzinc/claude-plugins/extract-quotes)<a href="https://agentmods.dev/commands/animalzinc/claude-plugins/extract-quotes"><img src="https://agentmods.dev/badge/commands/animalzinc/claude-plugins/extract-quotes.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.00898 |
| Opus 5 | $0.00005 | $0.00449 |
| Sonnet 5 | $0.00002 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
extract-quotes 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract Quotes by Topic
Find the most representative and compelling quotes about a specific topic from interview transcripts.
Step 1: Scan Transcripts
Search directory $2 for transcripts:
- Identify all transcript files
- Count total transcripts available
Report to user:
## 📁 Transcripts Found
**Directory:** $2
**Transcripts:** [number] files
**Topic to search:** "$1"
Proceeding to extract relevant quotes...
Step 2: Extract Relevant Quotes
Use the quote-selector agent to:
For each transcript:
- Search for mentions of topic "$1" (and related terms)
- Extract full quote with context
- Rate quote quality (clarity, insight value, brevity)
- Include speaker/participant attribution if available
Quote selection criteria:
- Relevant - Directly addresses the topic
- Insightful - Reveals something meaningful
- Clear - Standalone understandable
- Concise - Not overly long (prefer 1-3 sentences)
- Authentic - Conversational tone preserved
Step 3: Rank and Present Quotes
Default: Show top 10 quotes If --max-quotes specified: Show that many
Present to user:
## 💬 Quotes About: "$1"
Found [total number] relevant quotes across [number] transcripts.
Showing top [$3 or 10] by quality score.
---
### Quote 1 (Score: [X]/10)
> "[Full quote text]"
**Source:** [Transcript name / Participant ID]
**Context:** [Brief context if helpful - when/why this was said]
---
### Quote 2 (Score: [X]/10)
[Same format...]
---
## Quote Categories
**By theme:**
- [Sub-theme 1]: [count] quotes
- [Sub-theme 2]: [count] quotes
**By sentiment:**
- Positive: [count]
- Negative/Pain point: [count]
- Neutral: [count]
---
## Usage Tips
**To find more quotes:**
```bash
/extract-quotes "[topic]" [directory] --max-quotes 20
To search related terms:
/extract-quotes "pricing or cost or budget" [directory]
---
## Step 4: Optional - Export Quotes
**Ask user:**
Would you like to:
- Save these quotes to a file (quotes/$1-quotes.md)
- Copy to clipboard for pasting elsewhere
- Just view them here
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.
- 6d ago First seen · 169 lines · 0 tokens per session scan A d51015219fc8
extract-quotes is a command published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 16d ago), licensed MIT. It adds 9 tokens to every session and 898 once invoked, about $0.0000 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.
Other commands, from other repositories
brand-setup
Configure brand voice, terminology, compliance guardrails, and style guide for content production.
output-folder
Print the absolute path to the user-visible ContentForge output folder and open it in the OS file manager.
create-content
Run the full 10-phase content production pipeline — research, draft, fact-check, humanize, and publish.
audit-content
Audit your content library for freshness decay, coverage gaps, and optimization opportunities.
content-brief
Generate a research-backed content brief with keyword data, competitor analysis, search intent, and SEO strategy.
publish
Publish finished content to Webflow or WordPress with preview, verification, and HTML export fallback.