jesse-mcp: Instructions file for Codex

AGENTS.md

jesse-mcp AGENTS.md is an instructions file for Codex, OpenCode from bkuri/jesse-mcp. It costs 1,318 tokens per session, scanned A, original, from a forked repository, MIT.

Project instructions for developing Jesse MCP, an MCP server that exposes Jesse’s algorithmic-trading framework to AI agents.

In plain words
What is it for?
Use them when modifying or testing Jesse MCP, including its Python server, trading tools, REST API integrations, formatting, linting, and type checks.
Why use it?
They document the development commands, coding conventions, REST API details, and common integration mistakes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: names the TodoWrite tool.

This is bkuri/jesse-mcp's own configuration. It tells Codex and OpenCode how to work on jesse-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything jesse-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bkuri/jesse-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bkuri/jesse-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/bkuri/jesse-mcp

Made for: Codex, OpenCode.

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 jesse-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bkuri/jesse-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/bkuri/jesse-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/bkuri/jesse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bkuri/jesse-mcp/agents-md/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 jesse-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bkuri/jesse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bkuri/jesse-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,318 This file is loaded in full into every session.
When invoked 1,318 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
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 $0.01318 $0.01318
Opus 5.5 $0.00527 $0.00527
Sonnet 5.5 $0.00264 $0.00264
Haiku 4.5 $0.00132 $0.00132

Measured 2mo ago against content hash 4c3d4726ab02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jesse-mcp AGENTS.md 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 2mo 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.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jesse MCP Development Guidelines

MCP server exposing Jesse's algorithmic trading framework to LLM agents. 46 tools across 6 phases.

External References

  • jessegpt.md - Strategy writing, indicators, Jesse workflow
  • docs/jesse-rest-api.md - Full REST API payload structures

Build/Lint/Test

pip install -e .                # Install editable
pytest                           # Run tests
pytest -v -s tests/test_x.py     # Verbose with print
flake8 jesse_mcp/ && black jesse_mcp/ && mypy jesse_mcp/  # Lint/format/typecheck
python -m jesse_mcp              # Run server (stdio)
python -m jesse_mcp --transport http --port 8000  # Run server (HTTP)

Code Style

  • Formatting: black (88 chars), double quotes
  • Imports: stdlib → third-party → local (blank lines between)
  • Types: Use typing module (Dict[str, Any], Optional[T], etc.)
  • Naming: PascalCase classes, snake_case functions, UPPER_SNAKE_CASE constants
  • Errors: Return {"error": str(e), "error_type": type(e).__name__} from tools
  • Logging: logger = logging.getLogger("jesse-mcp.phase3"), emoji prefixes (✅❌⚠️)

Jesse REST API Gotchas

These are the common mistakes that cause silent failures:

  1. warm_up_candles in config - NOT at root level
  2. exchanges requires balance - Missing balance causes errors
  3. ID must be valid UUID - Use str(uuid.uuid4())
  4. Symbol format: BTC-USDT with hyphen
  5. Date format: YYYY-MM-DD string
  6. Strategy name: Case-sensitive, must match class exactly

See docs/jesse-rest-api.md for full payload structures.

Architecture Patterns

Lazy Initialization (allows testing without Jesse)

jesse = None
_initialized = False

def _initialize_dependencies():
    global jesse, _initialized
    if _initialized: return
    # ... init logic
    _initialized = True

Singleton with Getter

_optimizer_instance = None

def get_optimizer(use_mock=None) -> Phase3Optimizer:
    global _optimizer_instance
    if _optimizer_instance is None:
        _optimizer_instance = Phase3Optimizer(use_mock=use_mock)
    return _optimizer_instance

Read the full file on GitHub · 166 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. 2mo ago First seen · 166 lines · 1,318 tokens per session scan A 4c3d4726ab02

Subscribe to this mod's changes

jesse-mcp AGENTS.md is an instructions file published in the GitHub repository bkuri/jesse-mcp (23 stars, last pushed 5mo ago), licensed MIT. It adds 1,318 tokens to every session, about $0.0053 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

jesse-mcp AGENTS.md compared with instructions from other repositories

jesse-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
jesse-mcp AGENTS.mdbkuri/jesse-mcpInstructions file235mo agoMITA1,318Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode