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.
git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligenceWrote 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/agentii-ai/agentii-investment-intelligence/bio-pharm)<a href="https://agentmods.dev/plugins/agentii-ai/agentii-investment-intelligence/bio-pharm"><img src="https://agentmods.dev/badge/plugins/agentii-ai/agentii-investment-intelligence/bio-pharm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/agentii-ai/agentii-investment-intelligence/bio-pharm"><img src="https://agentmods.dev/badge/plugins/agentii-ai/agentii-investment-intelligence/bio-pharm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bio-pharm 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 6d 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.
What it actually says
{
"name": "bio-pharm",
"version": "0.1.0",
"description": "Biotech/pharma med vertical \u2014 FDA catalysts, pipelines, med sector analysis (spec 052)",
"author": {
"name": "agentii-ai",
"url": "https://agentii.ai"
}
}
What it installs
The manifest is a name and a version. 15 skills travel with it, and installing the plugin installs all of them — 1,016 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill fda-catalyst-medicines A 77 tokens
- Skill ct-status-diff A 115 tokens
- Skill fda-catalyst-devices A 64 tokens
- Skill fda-catalyst-vaccines A 64 tokens
- Skill market-share-tracking A 92 tokens
- Skill med-event-takeaways A 90 tokens
- Skill med-market-sizing A 70 tokens
- Skill peer-bench-med A 49 tokens
- Skill pipeline-devices A 42 tokens
- Skill pipeline-medicines A 60 tokens
- Skill pipeline-vaccines A 51 tokens
- Skill trial-readout-analysis A 77 tokens
- Skill earnings-preview-med A 50 tokens
- Skill recent-quarter-med A 52 tokens
- Skill sector-overview-med A 63 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.
- 6d ago Changed · +9 lines 394bc1834336
- 1mo ago First seen · 1 lines scan A b3f84da0c4db
bio-pharm is a plugin published in the GitHub repository agentii-ai/agentii-investment-intelligence (208 stars, last pushed yesterday), 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 2026-09-05.
Other plugins, from other repositories
bristol-os
Bristol OS — a multifamily real estate research teammate for Bristol Development Group. Deep research, site selection, market & comp analysis, investor & owner sourcing, underwriting research, deal memos, and pipeline tracking.
finance
Six-phase FP&A process — assess, plan, forecast, budget, model, review with 5 utility skills.
a-stock-skills
A set of tools for researching Chinese A-share stocks, including data retrieval, natural-language stock screening, holding analysis, and daily after-market routines. It is described as research software rather than financial advice.
findash
Personal finance system as Claude skills: sync bank, document, and IBKR evidence into SQLite, and explore it in a live local React dashboard. Skills: setup, fetch-bank-data, fetch-investments, sync-finance-data, and findash-doctor.
bankrecht
Bank- und Kapitalmarktrecht (Fachanwaltschaft). Kreditvertragsprüfung, Verbraucherdarlehen §§ 491 ff. BGB, Anlageberatung WpHG, MiFID II, Bauspar-/Hypothekenrecht.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.