analyze

analyze is a command for Claude Code from aavaz-ai/enterpret-claude-plugins. It costs 30 tokens per session (5,135 once invoked), scanned A, original, MIT.

A deep-analysis command for investigating a customer-feedback topic across trends, opinions, themes, related patterns, and direct evidence. An optional root-cause mode examines how serious a problem is and groups possible explanations.

In plain words
What is it for?
Use it to study changes in feedback volume, sentiment, theme relationships, and customer quotes. Add root-cause analysis when you need to assess severity, affected areas, and possible causes.
Why use it?
It replaces a series of separate manual searches with one structured investigation. It helps distinguish isolated comments from larger patterns and supports evidence-based diagnosis.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the enterpret-customer-insights plugin — 4 skills, 6 commands, 2 agents, 1 hook, 1 MCP server 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 commands/aavaz-ai/enterpret-claude-plugins/analyze
Clone the repo
git clone --depth 1 https://github.com/aavaz-ai/enterpret-claude-plugins

Made for: Claude Code.

Or install enterpret-customer-insights, the plugin that ships this one along with the rest of its 4 skills, 6 commands, 2 agents, 1 hook, 1 MCP server.

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 analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/aavaz-ai/enterpret-claude-plugins/analyze.svg)](https://agentmods.dev/commands/aavaz-ai/enterpret-claude-plugins/analyze)
Your own site
<a href="https://agentmods.dev/commands/aavaz-ai/enterpret-claude-plugins/analyze"><img src="https://agentmods.dev/badge/commands/aavaz-ai/enterpret-claude-plugins/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,135 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 5.1 $0.00030 $0.05135
Opus 5 $0.00015 $0.02567
Sonnet 5 $0.00006 $0.01027
Haiku 4.5 $0.00003 $0.00513

Measured 5d ago against content hash 243bb80e1414, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

analyze 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 5d 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.

commands/analyze.md · 534 lines

How it starts

The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/analyze

You are running a deep multi-query analysis of a customer feedback topic. This command builds a comprehensive picture: volume trends, sentiment breakdown, theme structure, co-occurring patterns, taxonomy placement, and verbatim evidence. It is the full investigation — not a quick scan.

With --rootcause, the same queries power a structured root cause analysis — severity assessment, blast radius, hypothesis clustering, and an evidence chain focused on diagnosing issues.

Pre-Flight

  1. Check if context/organization.json exists. If not, tell the user: "Run /start first to connect to your organization's Knowledge Graph." Stop.
  2. Read context/organization.json for org name, slug, and citationBaseUrl.
  3. Call get_organization_details from the enterpret-wisdom-mcp MCP server as a connectivity check. If it fails with an auth error, tell the user to run /start and stop.
  4. Read .claude/enterpret-customer-insights.local.md if it exists for user preferences (role, focus, output style).

Mode Detection

Determine which mode to run:

  1. Explicit flag: /analyze checkout --rootcause → rootcause mode
  2. Implicit detection: If the input looks like a bug report, Jira paste, or contains words like "broken", "failing", "regression", "outage", "crash", "error", "down" → suggest rootcause mode:

    "This looks like an issue investigation — want me to include severity assessment and root cause hypotheses? (y/n)"

    • If yes → rootcause mode
    • If no → standard mode
  3. Default: standard analysis mode

Set the mode variable {MODE} to either standard or rootcause for use in subsequent steps.

Skills (reference during execution, not upfront)

  • wisdom-kg — read if you need schema details or a query fails
  • evidence-synthesis — read when synthesizing quotes and writing the narrative
  • User context is loaded from .local.md above; defaults are in the wisdom-kg skill

Process

Step 1: Parse Input

Extract the topic from the user's input. Accept messy input — Jira ticket titles, vague descriptions, feature names, support escalation subjects.

Read the full file on GitHub · 534 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. 5d ago First seen · 534 lines · 30 tokens per session scan A 243bb80e1414

Subscribe to this mod's changes

analyze is a command published in the GitHub repository aavaz-ai/enterpret-claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 5,135 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.