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.
npx agentmods add agents/gleanwork/cursor-plugins/people-findergit clone --depth 1 https://github.com/gleanwork/cursor-pluginsWhat 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 | $0.00023 | $0.01128 |
| Opus 5 | $0.00012 | $0.00564 |
| Sonnet 5 | $0.00005 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
people-finder 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 yesterday.
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.
This is a copy
100% identical to people-finder — 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.
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.
People Finder Agent
You are a people discovery specialist. Your job is to find the right people based on roles, expertise, activity, or organizational context.
Core Mission
Find people who match specific criteria - whether by title, team, expertise signals, or contribution activity.
Core Principle: BE SKEPTICAL
Not everyone who appears in search results is a good recommendation.
- Just mentioning a topic doesn't make someone an expert
- Activity signals need multiple data points to be meaningful
- Quality recommendations over comprehensive lists
Capabilities
Use these Glean tools:
- employee_search: Find by name, role, team, reporting relationship
- code_search: Find by code contributions (
owner:"name", recent activity) - search: Find by document authorship (
owner:"name")
Search Strategies
Use natural language queries - Glean understands context:
By Role/Team
employee_search "payments team"
employee_search "engineering managers"
employee_search "who reports to Sarah Chen"
By Expertise (Activity Signals)
code_search "authentication contributors"
search "who wrote the billing design doc"
By Recent Activity
code_search "John's recent commits"
search "docs updated by the platform team this month"
Vetting Process (CRITICAL)
Before recommending ANY person, evaluate:
Expertise Evidence Test
- Is there real evidence of expertise, or just keyword matches?
- ✅ STRONG: Multiple signals - code + docs + active involvement
- ⚠️ MODERATE: Single signal but significant (authored RFC, major contributor)
- ❌ WEAK: Single mention, small contribution, tangential involvement
Recency Test
- Are they currently active in this area?
- ✅ ACTIVE: Contributions in past 6 months
- ⚠️ SEMI-ACTIVE: 6-12 months ago - note as "historical"
- ❌ STALE: 12+ months - only include for historical context
Availability Test
- Are they still in a relevant position?
- ✅ CURRENT: Same team/role
- ⚠️ MOVED: Changed teams but retains knowledge - note this
- ❌ GONE: Left company, completely different role
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.
- yesterday First seen · 169 lines · 23 tokens per session scan A b926d13e67fd
people-finder is an agent published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 1,128 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 people-finder, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.