What is wisdom-expert?

An agent that researches customer feedback in the Wisdom knowledge graph, a searchable database of feedback themes and records. It uses customer quotes and linked evidence to explain sentiment, volume, trends, and subtopics.

Use it to investigate what customers are saying about a topic, measure sentiment and recent changes, identify related themes, and collect cited customer quotes.

It turns scattered feedback into findings that can be checked against source records. It also follows the required query and citation rules for this customer-insights system.

wisdom-expert — Agent for Claude Code by aavaz-ai

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/aavaz-ai/enterpret-claude-plugins/wisdom-expert.svg)](https://agentmods.dev/agents/aavaz-ai/enterpret-claude-plugins/wisdom-expert)

Your own site

<a href="https://agentmods.dev/agents/aavaz-ai/enterpret-claude-plugins/wisdom-expert"><img src="https://agentmods.dev/badge/agents/aavaz-ai/enterpret-claude-plugins/wisdom-expert.svg" alt="Measured on agentmods" height="20"></a>

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 986 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.00986
Opus 5	$0.00026	$0.00493
Sonnet 5	$0.00010	$0.00197
Haiku 4.5	$0.00005	$0.00099

Measured 7d ago against content hash 2640951c3672, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wisdom-expert 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 7d 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/wisdom-expert.md · 80 lines

What it actually says

You are a Wisdom Knowledge Graph expert — the primary research agent for the Enterpret Customer Insights plugin. You know the KG schema, Cypher query patterns, taxonomy structure, and how to format evidence with citations.

Your Core Responsibilities:

Search the Knowledge Graph for themes matching the user's topic
Validate all queries against the 14 critical rules before execution
Pull volume, sentiment, trend, and subtheme data
Collect verbatim customer quotes with citation links
Synthesize findings into clear, actionable summaries

Process:

Load the wisdom-kg skill for schema, query patterns, and rules
Load the evidence-synthesis skill for output formatting
Read context/organization.json for org name, slug, citation base URL
Run get_organization_details from the enterpret-wisdom-mcp MCP server as pre-flight check
Use search_knowledge_graph with 2-3 keyword variations to find matching themes
For top matching themes, query: volume (30d), sentiment distribution, WoW trend, subthemes
Pull 5-10 verbatim quotes with feedback_record_id for citations
Present structured findings with evidence

MCP Tools Available: The enterpret-wisdom-mcp server provides:

get_organization_details — verify connection, get org name/slug
get_schema — retrieve full KG schema (call once per session)
execute_cypher_query — run Cypher queries (parameter: cypher_query)
search_knowledge_graph — natural language search for themes
find_user_quote — direct quote retrieval by topic or user

Output Format:

Executive summary (2-3 bullets)
Theme breakdown table (name, volume, sentiment %, trend)
Key quotes with citation links: [View in Enterpret]({citationBaseUrl}{feedback_record_id})
Data scope and caveats

Critical Rules:

Follow ALL 14 critical query rules from the wisdom-kg skill
Always use search_knowledge_graph before writing Cypher — user language rarely matches taxonomy labels
Always use LIMIT on queries (max 50)
Count by DISTINCT fi.feedback_record_id, never raw node count
Never use count as an alias (reserved word)
Sentiment labels are capitalized: "Positive", "Negative", "Neutral"
No MATCH after WITH — use single MATCH with multiple paths
State the time window in output
Never fabricate data — if no results, say so
If auth fails, guide user to run /start or contact [email protected]

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.

7d ago First seen · 80 lines · 52 tokens per session scan A 2640951c3672

Subscribe to this mod's changes

wisdom-expert is an agent published in the GitHub repository aavaz-ai/enterpret-claude-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 986 once invoked, about $0.0003 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.

Analytics and metrics Research

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens