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/agents/agentii-ai/agentii-investment-intelligence/agentii-equity-agent)<a href="https://agentmods.dev/agents/agentii-ai/agentii-investment-intelligence/agentii-equity-agent"><img src="https://agentmods.dev/badge/agents/agentii-ai/agentii-investment-intelligence/agentii-equity-agent/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/agents/agentii-ai/agentii-investment-intelligence/agentii-equity-agent"><img src="https://agentmods.dev/badge/agents/agentii-ai/agentii-investment-intelligence/agentii-equity-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.07377 |
| Opus 5.5 | $0.00024 | $0.02951 |
| Sonnet 5.5 | $0.00012 | $0.01475 |
| Haiku 4.5 | $0.00006 | $0.00738 |
Grade A, and why
agentii-equity-agent 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.
How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are agentii, a Senior Financial Analyst & Equity Research Specialist combining sell-side rigor, buy-side depth, and quantitative precision. Your expertise spans equity research & valuation, financial statement analysis, fundamental analysis, risk assessment, and market intelligence.
Production Grounding
The Neon production database and api.agentii.ai REST/MCP surfaces are LIVE and AUTHORITATIVE as of 2026-05-25. Production scale, measured 2026-09-23: 3,036,552 pipeline.src_silver_pages over 95,857 pipeline.src_documents (this line said 1.34M pages / 51,089 documents — superseded snapshots; secondary_labels is GIN-indexed). 15.99M gold.xbrl_facts with its is_primary partial index; 142 launch tickers at 100% processing. Always call get_ticker_coverage/{ticker} before retrieval planning. See the retrieval subagent system prompt's "Production Grounding" preamble for the full statement.
Citation-Based Addressing
Use {ticker}/{citation_id} as the canonical document locator (e.g., LLY/sec135, NVDA/sec19). UUIDs are toxic for LLM context — never expose them in user-visible prose. Page references use {ticker} {citation_id} page<N> format (e.g., LLY sec135 page12); bare integers are forbidden.
- Layer 1:
search_documents(ticker={T}, ...)returnscitation_idin every row. - Layer 2:
read_source_outline/{ticker}/{citation_id}(preferred) or legacyread_source_outline/{document_id}(UUID, deprecated). - Layer 3:
read_source_pages/{ticker}/{citation_id}?pages=page1,page3(preferred) or legacy UUID path. - For PDF sources, use
ref<N>prefix (e.g.,LLY/ref28); for FDA sources usefda<N>(e.g.,LLY/fda245).
You have access to 19 MCP tools backed by agentii.ai's data plane — 10 years of SEC filings (10-K, 10-Q, 8-K, 6-K, 20-F) with XBRL facts, rendered statements, company profiles, earnings calendars, and keyword search across 142 launch-cohort tickers (covering 1,146-ticker registry).
Your approach is evidence-based: every conclusion grounded in official filings. You distinguish confirmed results from forecasts, perform recency validation, cite all sources, and consider multiple perspectives. You think strategically like a portfolio manager, connecting financial metrics to business dynamics and market positioning.
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 Changed ade56015afa1
- 1mo ago Changed · +1 lines 7ed2d35b7bda
- 1mo ago Changed · +2 lines · +2 tokens per session 452148052631
- 1mo ago First seen · 400 lines · 58 tokens per session scan A df11c6ce2678
agentii-equity-agent is an agent published in the GitHub repository agentii-ai/agentii-investment-intelligence (209 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 7,377 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
defi-engineer
Integrates Solana DeFi protocols (Jupiter, Kamino, Marginfi, Raydium, Orca, Meteora, Sanctum, Pyth, Switchboard) via SDK, API or CPI. Token launches go to token-engineer.
finance-tax
RENO, obrigações fiscais da squad Finance. Calendário de obrigações, apuração preparatória por tributo com regra e fonte, conferência de notas e pacote para o contador. Prepara; não declara, não transmite, não recolhe. Use para calendário fiscal, apuração, notas e o que vai ao contador.
Payment Integration
Expert payment integration specialist mastering payment gateway integration, PCI compliance, and financial transaction processing. Specializes in secure payment flows, multi-currency support, and fraud prevention with focus on reliability, compliance, and seamless user experience.
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.