Option Desk
Options research with a local dashboard, agent skills, and MCP tools. Import a chain, inspect its Greeks and positioning, compare structures, and keep the results as readable files.
Contents
On this page
- See the desk
- Get started
- Ask your agent
- Follow a research workflow
- Read the documentation
- Development
- Licensing
Guides and wiki
See the desk
The dashboard brings the chain, model assumptions, and research results onto one page. These are captures of the current local dashboard with synthetic teaching inputs. They are not market observations or evidence of trading performance. Capture details distinguish the input scenario from the capture date.
Dashboard tour
Open an image for its full resolution. The complete gallery includes individual panels and charts. The dashboard guide explains how to read them.
| Positioning | Volatility |
|---|---|
 |  |
| Inspect the assumed dealer exposure and chain coverage. | Compare strikes and expiries without hiding missing values. |
| Structure payoff | Two-expiry structures |
|---|---|
 |  |
| Read the legs, breakevens, and limits together. | Inspect the valuation assumptions for the surviving leg. |
| Simulation | Backtest |
|---|---|
 |  |
| Read the fan with the convergence diagnostics. | Read outcomes with the benchmark and model limitations. |
| Composite comparison | Contract ladder |
|---|---|
 |  |
| Inspect the formula and disagreements between models. | Compare sensitivities and payoff shapes. |
Get started
Choose one route:
Try the supplied sample
Requirements: Git and Python 3.11 or later. Run these commands on macOS or Linux:
git clone https://github.com/Iman/agent-driven-options-desk-and-skills.git
cd agent-driven-options-desk-and-skills
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e ./engine -e ./shell
optiondesk chain SYNTH --from-file examples/chain-synth.json --accept-data-rights --out-dir artifacts/tutorial
optiondesk greeks --out-dir artifacts/tutorial
optiondesk exposure --out-dir artifacts/tutorial
optiondesk compare --out-dir artifacts/tutorial
optiondesk dashboard --out-dir artifacts/tutorial
Open http://127.0.0.1:8787 on the same computer.
Select SYNTH and 2026-10-08.
Press Ctrl+C in the terminal to stop the server. The result files remain in artifacts/tutorial.
The supplied sample contains 62 synthetic contracts and a fixed valuation scenario. It needs no external provider after installation. The walkthrough includes Windows activation, expected results, and the next steps. Sample provenance explains the inputs.
Install the full local desk
From a checkout, run:
./install.sh
optiondesk doctor
This installs the local tools and skills and attempts MCP registration with supported runtime CLIs it finds. Installation covers paths, flags, Docker, and removal. A plugin installation alone does not install the local calculation engine.
For an existing local provider setup, run the complete demonstration:
./run.sh --symbols SPY
The runner retrieves data, builds the research artifacts, opens a paper position, and serves the dashboard.
It writes to ~/TradingDesk/option-desk-demo by default.
Use --dry-run to inspect its commands.
Read provider setup before enabling Yahoo access.
Ask your agent
Install skills in your product
The installation guide includes single-skill and all-skill commands, user/project scope, ZIP preparation, and connection checks.
After connecting the local tools, ask:
Use examples/chain-synth.json, the supplied synthetic teaching sample.
I can use this file for private analysis.
Save the results under artifacts/tutorial.
Show its Greeks and positioning, then compare an iron condor with a straddle.
State the source, missing inputs, model assumptions, and degradation first.
The local MCP server exposes 12 tools. The hosted service supports a smaller workflow: snapshot validation, Greeks, positioning, and strategy plots. Simulation and backtests remain local workflows. See agent setup and prompts.
Follow a research workflow
The dashboard reads saved artifacts. It does not fetch new data when you open the page.
Use the same --out-dir for related commands and the dashboard.
The results guide explains how to interpret each stage.
Read the documentation
Where the desk is listed
Directory listings describe the hosted endpoint or the repository as they were on the date shown. The listing pages are maintained on each directory, not in this repository.
Development
Testing and coverage covers happy and failure paths, BDD scenarios, integration checks, and the 80% unit line-coverage gate per package.
Run from the repository root with the development dependencies installed. See Development for environment setup and screenshot capture.
python -m pytest engine/tests -q # 355 tests
python -m pytest shell/tests -q # 574 tests
python -m pytest agent/tests -q # 161 tests
python -m pytest -q # 1090 tests
These are collection counts, not a claim that this documentation edit ran every test. The workflow badge links to the actual CI result.
python3 scripts/refresh.py --no-index
python3 scripts/mutate.py --list
Ten stages in a full run rebuild generated documents and packages, check recorded evidence, and run the suites and repository rules. The mutation harness defines ninety-nine mutations. Use its output to distinguish detected changes, survivors, and skipped cases.
Eight schemas under shell/src/optiondesk/contracts/ define the artifact interface: 8 schemas + validator.
See the architecture guide for their roles.
The evidence record pins an earlier chain measurement to 2026-08-30T14:12:17+00:00.
It records 607 contracts, spot, listed expiries and 595 solved, 12 refused as unidentified.
These are historical evidence strings, not counts for the sample or the current screenshots.
The recorder retains them here for its existing documentation checks.
Contribute · Backlog · Changelog · Security
Licensing
The repository uses PolyForm Noncommercial 1.0.0. It is source available and free for noncommercial use. Commercial use requires a separate written agreement. See LICENSES.md. The software license does not grant rights to provider data.
Research software. No order placement. Model results are not fills, recommendations, or investment advice. Read the disclaimer, privacy policy, and third-party notices.