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.
/plugin marketplace add yuping322/financial-services-plugins-newnpx agentmods add plugins/yuping322/financial-services-plugins-new/private-equitygit clone --depth 1 https://github.com/yuping322/financial-services-plugins-newWrote 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/plugins/yuping322/financial-services-plugins-new/private-equity)<a href="https://agentmods.dev/plugins/yuping322/financial-services-plugins-new/private-equity"><img src="https://agentmods.dev/badge/plugins/yuping322/financial-services-plugins-new/private-equity.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
private-equity 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.
What it actually says
{
"name": "private-equity",
"version": "0.1.0",
"description": "Private equity deal sourcing and workflow tools: company discovery, CRM integration, and founder outreach",
"author": {
"name": "Anthropic FSI"
}
}
What it installs
The manifest is a name and a version. 9 skills, 9 commands travel with it, and installing the plugin installs all of them — 71 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill value-creation-plan A 0 tokens
- Skill dd-checklist A 0 tokens
- Skill dd-meeting-prep A 0 tokens
- Skill deal-sourcing A 0 tokens
- Skill unit-economics A 0 tokens
- Skill ic-memo A 0 tokens
- Skill returns-analysis A 0 tokens
- Skill deal-screening A 0 tokens
- Skill portfolio-monitoring A 0 tokens
- Command dd-prep A 8 tokens
- Command portfolio A 4 tokens
- Command returns A 8 tokens
- Command source A 9 tokens
- Command dd-checklist A 5 tokens
- Command ic-memo A 5 tokens
- Command screen-deal A 10 tokens
- Command unit-economics A 14 tokens
- Command value-creation A 8 tokens
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 · 9 lines scan A cce88415074f
private-equity is a plugin published in the GitHub repository yuping322/financial-services-plugins-new (17 stars, last pushed 5mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
flagship
Conduct many concurrent Claude Code sessions as one portfolio — the layer above ship-armada, for when the work is already spread across a dozen live sessions rather than waiting in one repo's backlog. Builds a roster of every peer session, learns what each owns, and coordinates them over SendMessage: hands out a…
scala
S.C.A.L.A. AI OS — Run your entire business from Claude. CRM, invoicing, bookings, SARA AI assistant, 20 industry verticals, 250M+ company database.
investor-relations-mcp
FastMCP server for tracking a seed raise investor pipeline from Claude Code. Syncs from Obsidian vault CRM files, generates meeting prep documents, tracks interactions, and monitors follow-up compliance.
igpt-executive
Executive intelligence skills powered by iGPT. Builds board updates, tracks investor relationships, logs strategic commitments, monitors key relationship health, detects crisis signals, and tracks fundraising threads — all automatically from connected email datasources.
goal-mode
Better Goal — long-horizon autonomous mode for Claude Code: hierarchical plan-tree (Sprint→Epic→Task) with acceptance criteria, review-gates, and a triple budget. Codex /goal analog.
enterprise-team
Complete virtual company with 76 specialized AI agents across Engineering, Product, Infrastructure, Data, Security, Marketing, Sales, Finance, Legal, and People. Pipeline modes (Full/Sprint/Micro), Dev↔QA loops, quality gates, and handoff protocols.