Directory / AKzar1el/clockcross

AKzar1el/clockcross

Evidence-gated autonomous AI options agent for COIN using BTC/COIN repricing signals, bounded LLM adjudication, deterministic risk controls, and Alpaca paper MLeg execution.

Reviewed New (under 90 days old) AI agent 84/100

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 d9ed871, rubric v1.1.

Reviewer summary: Hackathon agent that only trades Alpaca paper spreads on COIN. The risk code in src/clockcross/trading/risk.py caps loss per position and in aggregate against equity and buying power. The config rejects non-paper URLs, so there is no live path, but I found no kill switch.

Facts

Repository	https://github.com/AKzar1el/clockcross
Type	AI agent
Strategies	Credit spreads
Brokers	Alpaca
License	MIT
Language	Python
Last commit	2026-09-04 (51 days before the scan)
Last scanned	2026-10-24
Stars	0 (shown for context, never scored)

Score breakdown

Factor	Points	How it was decided
Risk limits and kill switch	10 / 20	Real position and aggregate loss caps in trading/risk.py (10). No kill switch or halt flag found; the scanner's other evidence came from docs and research artifacts. Reviewer confirmed the scanner result. Scanner evidence (6, automated, can include false matches) `artifacts/research/indicative-surface-robustness-2026-09-01.json:23` [max loss] "max_loss": 613.0, `src/clockcross/agent/prompts.py:15` [position limit] - You cannot override symbol restrictions, option feasibility, quote freshness, contract construction, position sizing, portfolio risk, buyi `src/clockcross/research/surface_robustness.py:171` [risk limit] risk_cap = max_net_debit * _CONTRACT_MULTIPLIER `docs/research/2026-09-04-featherless-phase2.md:53` [max contracts] - DeepSeek-V4-Pro produced valid schema but failed the unanimity requirement; its recorded model availability was also `offline` during the `docs/superpowers/specs/2026-08-29-clockcross-design.md:209` [daily loss limit] - modify portfolio risk limits; `docs/superpowers/specs/2026-08-31-competition-runtime-hardening.md:30` [stop loss] The research horizon is `forward_60m_return`, measured from the 09:55 ET decision boundary to 10:55 ET. The competition runtime therefore us
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	12 / 15	50 days since last commit Fact from the commit date, no judgment involved. Scanner evidence (1, automated, can include false matches) `default branch HEAD` 2026-09-04 (50 days ago)
Tests	15 / 15	223 test cases found in 56 test files; CI test step found Reviewer confirmed the scanner result. Scanner evidence (4, automated, can include false matches) `tests/integration/test_alpaca_historical_contract.py:1` 1 test case `tests/test_no_secrets.py:1` 2 test cases `tests/unit/test_adjudicator.py:1` 8 test cases `.github/workflows/ci.yml:32` run: uv run pytest -q
Paper or dry-run mode	15 / 15	RunMode is dry-run or paper, and config.py rejects any non-paper endpoint. Reviewer confirmed the scanner result. Scanner evidence (4, automated, can include false matches) `README.md:9` ClockCross was built for the Alpaca AI Trading Agents Hackathon. It uses Alpaca's paper-trading stack, Alpaca MCP, an authenticated Clou `.env.example:3` [paper-mode flag] ALPACA_TRADING_BASE_URL=[link] `.env.example:3` [paper endpoint] ALPACA_TRADING_BASE_URL=[link] `src/clockcross/runtime.py:17` [dry-run flag] RunMode = Literal["dry-run", "paper"]
README quality	7 / 10	install steps, config or env vars, 15452 chars Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `README.md:1` README with 15452 characters
Broker detection	10 / 10	Alpaca (deps, code, readme) Reviewer confirmed the scanner result. Scanner evidence (1, automated, can include false matches) `pyproject.toml:18` [Alpaca: deps+code+readme] "alpaca-py>=0.42,<1",
Total	84 / 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/akzar1el--clockcross.json from it. Badges show the grade and whether it was reviewed. Maintainers may use one without asking.