Directory / trevorgordon981/Agentic-Trader

trevorgordon981/Agentic-Trader

LLM-assisted options swing trading: the model proposes trades, you approve each entry, risk rails + an exit manager keep the book bounded. Sanitized public release.

Reviewed AI agent 89/100

Not financial advice. A grade measures public repo hygiene only (license, upkeep, tests, paper mode, risk limits, docs). It does not measure returns, safety or suitability. Options trading can lose more than you invest. Read the full policy.

Reviewed. Grok Bot read the code and docs and checked or adjusted each judged factor. Nothing was executed. This is not a human audit. Reviewed on 2026-10-24 against commit 85e3fb4, rubric v1.1.

Reviewer summary: LLM-proposed trades gated by deterministic code: config.yaml kill_switch, daily notional and per-cycle order caps, Slack approval for sells and a very large test suite with CI. It has no documented paper mode, only dry-run and shadow flags.

Facts

Repository	https://github.com/trevorgordon981/Agentic-Trader
Type	AI agent
Strategies	Not tagged
Brokers	Interactive Brokers
License	MIT
Language	Python
Last commit	2026-10-09 (16 days before the scan)
Last scanned	2026-10-24
Stars	4 (shown for context, never scored)

Score breakdown

Factor	Points	How it was decided
Risk limits and kill switch	20 / 20	config.yaml has a kill_switch block, max_notional_per_day and max_orders_per_cycle; sells need Slack approval. Reviewer confirmed the scanner result. Scanner evidence (6, automated, can include false matches) `backfill_from_exits_log.py:195` [stop loss] "sl_hit": (reason in ("stop", "sl", "stop_loss")), `calibrate_conviction_sizing.py:371` [risk limit] "wire it into run_trader.py's RiskLimits (mirror conviction_size_curve)."), `config.yaml:21` [max notional or exposure] max_notional_per_day: 50000.0 `config.yaml:19` [max orders] max_orders_per_cycle: 5 `daily_recommend.py:964` [max loss] idea.max_loss_usd = resolved.credit_max_loss_usd `config.yaml:12` [kill switch] kill_switch:
License	15 / 15	MIT (OSI approved) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `LICENSE:1` License file
Last commit on default branch	15 / 15	15 days since last commit Fact from the commit date, no judgment involved. Scanner evidence (1, automated, can include false matches) `default branch HEAD` 2026-10-09 (15 days ago)
Tests	15 / 15	2892 test cases found in 232 test files; CI test step found Reviewer confirmed the scanner result. Scanner evidence (4, automated, can include false matches) `tests/test_admission_broker_topology.py:1` 7 test cases `tests/test_admission_transaction.py:1` 44 test cases `tests/test_alert_throttle.py:1` 15 test cases `.github/workflows/ci.yml:12` pytest:
Paper or dry-run mode	7 / 15	Dry-run on close_symbol and a shadow-only flag exist in code, but the README only advises paper testing and does not document a mode (7). Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `backfill_from_exits_log.py:223` [dry-run flag] def backfill(exits_path, trades_path, out_path, decision_dir, dry_run):
README quality	7 / 10	install steps, config or env vars, 4192 chars Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `README.md:1` README with 4192 characters
Broker detection	10 / 10	Interactive Brokers (deps, code, readme) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `requirements.txt:2` [Interactive Brokers: deps+code+readme] ib_async==2.1.0 ; python_version >= '3.10'
Total	89 / 100	Grades: A 85+, B 70+, C 55+, D 40+, F below.

Grades measure public repo hygiene on the scan date. They say nothing about profits, safety or security. We did not run this code. Full rubric and patterns.

Something wrong?

Report a correction Request removal (maintainers)

Corrections and removals are public GitHub issues. We reply within 7 days and every change is in the repo history. Sponsors get no special treatment: see our policy.

Badge for your README

Once the site has a public address, shields.io can read /badge/trevorgordon981--agentic-trader.json from it. Badges show the grade and whether it was reviewed. Maintainers may use one without asking.