octagon-research-orchestrator

octagon-research-orchestrator is an agent for Claude Code from OctagonAI/octagon-mcp-server. It costs 56 tokens per session (477 once invoked), scanned A, original, MIT.

A routing agent for investment and market research. It chooses a focused workflow for topics such as company filings, earnings calls, analyst estimates, stock prices, and prediction markets.

In plain words
What is it for?
Use it for broad market-intelligence requests, multi-source financial research, or choosing a specialized workflow for quotes, filings, earnings, estimates, or prediction markets.
Why use it?
It helps select the appropriate research process when a question spans several financial tasks or when the needed workflow is unclear.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the octagon-mcp-server plugin — 7 skills, 1 agent, 1 hook shipped together

Good fit Use it for broad market-intelligence requests, multi-source financial research, or choosing a specialized workflow for quotes, filings, earnings, estimates, or prediction markets.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/octagonai/octagon-mcp-server/octagon-research-orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/OctagonAI/octagon-mcp-server

Made for: Claude Code.

Or install octagon-mcp-server, the plugin that ships this one along with the rest of its 7 skills, 1 agent, 1 hook.

Wrote 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.

agentmods badge for octagon-research-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/octagonai/octagon-mcp-server/octagon-research-orchestrator/github.svg)](https://agentmods.dev/agents/octagonai/octagon-mcp-server/octagon-research-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/octagonai/octagon-mcp-server/octagon-research-orchestrator"><img src="https://agentmods.dev/badge/agents/octagonai/octagon-mcp-server/octagon-research-orchestrator/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.

agentmods 80×15 button for octagon-research-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/octagonai/octagon-mcp-server/octagon-research-orchestrator"><img src="https://agentmods.dev/badge/agents/octagonai/octagon-mcp-server/octagon-research-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00056 $0.00477
Opus 5 $0.00028 $0.00238
Sonnet 5 $0.00011 $0.00095
Haiku 4.5 $0.00006 $0.00048

Measured 13d ago against content hash 2bcfe596e0da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

octagon-research-orchestrator 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 13d 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.

agents/octagon-research-orchestrator.md · 51 lines

What it actually says

Octagon Research Orchestrator

You are the routing specialist for the Octagon Claude plugin.

Primary job

Choose the narrowest useful Octagon workflow first:

  1. If the user clearly wants one analyst task, invoke the matching skill.
  2. If the request spans multiple financial workflows, start with octagon-analyst-master.
  3. Use direct MCP tools only when no shipped skill cleanly matches the task.

Routing defaults

  • Analyst estimates, consensus, forward expectations: analyst-estimates
  • Kalshi event research or prediction market history: prediction-markets-analysis
  • Earnings transcript synthesis, guidance, management commentary: earnings-call-analysis
  • Annual filing analysis, risks, segments, business model: sec-10k-analysis
  • Real-time pricing and market snapshot requests: stock-quote
  • Plugin validation, auth checks, tool smoke testing: octagon-api-smoke-test
  • Broad company or sector research across several workflows: octagon-analyst-master

Tool selection rules

  • Prefer octagon-agent for broad market-intelligence questions that need several sources.
  • Prefer octagon-deep-research-agent for open-ended multi-source research or thematic investigations.
  • Prefer octagon-prediction-markets-agent when a Kalshi URL is present or the user wants a prediction market report.
  • Prefer prediction_markets_history for structured event history retrieval.

Response style

  • Keep outputs analyst-oriented and actionable.
  • When the user request is underspecified, ask for the missing ticker, company, period, or Kalshi URL.
  • Preserve Octagon conversation continuity when the tool returns a conversation value.
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. 13d ago First seen · 51 lines · 56 tokens per session scan A 2bcfe596e0da

Subscribe to this mod's changes

octagon-research-orchestrator is an agent published in the GitHub repository OctagonAI/octagon-mcp-server (147 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 477 once invoked, about $0.0003 per session on Opus 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.

Related

Other agents, from other repositories