jesse-strategy-tests

A guide for testing strategy behavior in Jesse’s trading backend. Jesse is a trading framework, and a strategy defines when trades open, change, and close.

In plain words
What is it for?
Use it when testing entries, exits, take-profit or stop-loss rules, position lifecycle events, or closed-trade measurements in Jesse.
Why use it?
It keeps strategy tests consistent by running a backtest while placing the detailed checks inside the strategy’s lifecycle methods.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jesse-ai/jesse/jesse-strategy-tests
Any agent
npx skills add jesse-ai/jesse --skill jesse-strategy-tests
Clone the repo
git clone --depth 1 https://github.com/jesse-ai/jesse

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02565
Opus 5 $0.00000 $0.01282
Sonnet 5 $0.00000 $0.00513
Haiku 4.5 $0.00000 $0.00257

Measured yesterday against content hash d00a06270c59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jesse-strategy-tests 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.

.claude/skills/jesse-strategy-tests/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing tests for Jesse's backend

When a feature is tied to strategy behavior, write it the way the rest of the suite does: a tiny test function that runs a backtest against a purpose-built test strategy, where the assertions live inside the strategy's lifecycle hooks — not in the test function.

The pattern (canonical example)

1. The test — a one-liner in tests/test_parent_strategy.py that just runs the strategy:

def test_on_close_position():
    single_route_backtest('TestOnClosePosition')

2. The strategyjesse/strategies/TestOnClosePosition/__init__.py. The class name, the directory name, and the string passed to single_route_backtest must all match:

from jesse.strategies import Strategy
import jesse.helpers as jh
from jesse import utils


class TestOnClosePosition(Strategy):
    def should_long(self):
        return self.price == 10

    def go_long(self):
        if self.price == 10:
            self.buy = 1, self.price

    def on_open_position(self, order):
        self.take_profit = 1, 12  # close the position at 12

    def on_close_position(self, order, closed_trade) -> None:
        assert closed_trade.exit_price == 12
        assert closed_trade.entry_price == 10
        assert closed_trade.qty == 1
        assert closed_trade.type == "long"
        assert closed_trade.timeframe == self.timeframe
        assert closed_trade.exchange == self.exchange
        assert closed_trade.symbol == self.symbol

The assertions run during the backtest, inside on_close_position. If any fail, the backtest raises and the test fails. The test function itself stays assertion-free.

How the price moves (so triggers like self.price == 10 work)

single_route_backtest('Name') defaults to: futures, leverage 1, fee 0, 1m timeframe, up-trend, 100 candles. The up-trend candles have close prices 1, 2, 3, … , 99 (candles_from_close_prices(range(1, 100))). So self.price walks 1 → 99, one step per candle. That's why:

  • should_long / go_long fire when self.price == 10 (the 10th candle),
  • a take_profit at 12 fills two candles later as price rises through it.

Read the full file on GitHub · 256 lines

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. yesterday First seen · 256 lines · 0 tokens per session scan A d00a06270c59

Subscribe to this mod's changes

jesse-strategy-tests is a skill published in the GitHub repository jesse-ai/jesse (8,397 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,565 tokens. 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 skills, from other repositories

decker

Use when user asks about Decker signals, portfolio, orders, auto-order rules, news digest, Slack/Telegram integration, or exchange API key setup. Triggers (ko): 하이, 안녕, 시그널, 포지션, 수익현황, 매수해줘, 매도해줘, 자동주문, 청산해줘, 텔레그램 연동, 말만 하면, 뭐 할 수 있어, 어떻게 써, 처음인데, 단계별로, 시장 상태, 종목 비교, 뉴스, 소식, 다이제스트, HL, Polymarket, Hyperliquid, 바이낸스 키…

gigshow/decker-ai · 283 tokens

decker-developer

Use when a developer asks about Decker's Public API — obtaining API keys, authentication, rate limits, signal endpoints, SDK usage. Triggers: API key, dklive, X-API-Key, public API, /public/signals, REST API, developer, integrate Decker, rate limit.

gigshow/decker-ai · 66 tokens

decker-hyperliquid

Use when user asks about Hyperliquid DEX trading via Decker. Triggers: HL, 하이퍼리퀴드, DEX, 영구선물, HL 매수, HL 포지션, Hyperliquid 시세. Includes Safety Guidelines (position sizing, slippage).

gigshow/decker-ai · 68 tokens

decker-polymarket

Use when user asks about Polymarket prediction market via Decker. Triggers: Polymarket, 폴리마켓, 예측시장, PM 매수, PM 시장 검색, PM 카테고리, PM 이벤트, 시장 slug, YES/NO.

gigshow/decker-ai · 61 tokens

high-risk

High-risk overlay for Bitkub swing trading. Up to 3% risk per trade, BTC + ETH + top-10 altcoins allowed, no minimum cash reserve floor, shorter entry timeframe. Use when asked to trade aggressively, maximize returns, or "high risk". Applies looser filters on top of the playbook — read this first, then follow the…

dvgamerr-app/gokub-mcp · 100 tokens

playbook

Playbook for swing-trading the long side on Bitkub (THB pairs) using the gokub-mcp tools. Use when asked to find a trade, screen coins, evaluate an entry, size a position, place/manage an order, or review trading performance on Bitkub. Encodes the risk rules, the screen→regime→signal→size→validate→place→manage→log…

dvgamerr-app/gokub-mcp · 97 tokens