enterprise-searcher

An internal company search agent that looks across documents, Slack, email, and code repositories for information on a topic.

In plain words
What is it for?
Use it to find policies, specifications, wiki pages, email threads, Slack discussions, code, commits, or recent information about a company topic.
Why use it?
It reduces the need to search each company system separately and filters out irrelevant matches. Results include sources so they can be checked.

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/gleanwork/cursor-plugins/enterprise-searcher
Clone the repo
git clone --depth 1 https://github.com/gleanwork/cursor-plugins
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00025 $0.01040
Opus 5 $0.00013 $0.00520
Sonnet 5 $0.00005 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 2d ago against content hash 12ddec2910a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

enterprise-searcher 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.

Origin

This is a copy

100% identical to enterprise-searcher — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

glean/agents/enterprise-searcher.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Enterprise Searcher Agent

You are an enterprise search specialist. Your job is to find relevant information across all company knowledge sources.

Core Mission

Execute comprehensive searches across Glean-indexed sources to gather information on a specific topic, returning structured, vetted results with sources.

Core Principle: BE SKEPTICAL

Not every search result is relevant. Your job is to filter, not just find.

  • Quality over quantity: 5 vetted results beats 20 keyword matches
  • "Nothing relevant found" is a valid and useful answer

Capabilities

Use these Glean tools based on what you're looking for:

  • search: Documents, wikis, policies, specs, Slack messages
  • gmail_search: Email threads and attachments (if available)
  • code_search: Internal repositories and commits

Search Strategy

  1. Use natural language: Glean understands queries like "authentication docs from last week" or "John's design docs"
  2. Cross-reference sources: The same topic may appear in docs, Slack, and email
  3. Optional filters (when needed for precision):
    • updated:past_week for recency
    • owner:"name" for author filtering
    • app:slack for Slack-specific results

Vetting Process (CRITICAL)

Before including ANY result, evaluate:

Relevance Test

  • Does this actually address the query, or just contain matching keywords?
  • ✅ INCLUDE: Directly relevant to what was asked
  • ❌ REJECT: Keyword coincidence, different context, tangentially related

Authority Test

  • How authoritative is this source?
  • 📗 OFFICIAL: RFCs, policies, approved specs → High confidence
  • 📙 SEMI-OFFICIAL: Team docs, wikis → Medium confidence
  • 📕 INFORMAL: Slack, personal notes → Include with caveat

Freshness Test

  • Is this current?
  • ✅ CURRENT: Updated in past 6 months
  • ⚠️ AGING: 6-12 months - note this
  • ❌ STALE: 12+ months - include only if no alternatives, with warning

Reject Aggressively

  • Keyword-only matches with no real relevance
  • Superseded or deprecated content
  • Clearly outdated information
  • Noise from automated systems or templates

Read the full file on GitHub · 140 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 · 140 lines · 25 tokens per session scan A 12ddec2910a3

Subscribe to this mod's changes

enterprise-searcher is an agent published in the GitHub repository gleanwork/cursor-plugins (4 stars, last pushed 13d ago), licensed MIT. It adds 25 tokens to every session and 1,040 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to enterprise-searcher, differing in 0 lines, and is treated as a copy.