mangrove-agent: Instructions file for Claude Code

CLAUDE.md

mangrove-agent CLAUDE.md is an instructions file for Claude Code from MangroveTechnologies/mangrove-agent. It costs 874 tokens per session, scanned A, original, MIT.

Project instructions for a local trading bot that lets developers write strategies, test them against past data, practise trades, and eventually trade live.

In plain words
What is it for?
Use it when developing or modifying the Mangrove trading bot, its REST or MCP interfaces, strategy evaluation, trade records, or saved execution state.
Why use it?
It explains the bot’s architecture, rules, configuration, and ownership of trading records so code changes follow the project’s intended design.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is MangroveTechnologies/mangrove-agent's own configuration. It tells Claude Code how to work on mangrove-agent 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 mangrove-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MangroveTechnologies/mangrove-agent. 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/MangroveTechnologies/mangrove-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agent

Made for: Claude Code.

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 mangrove-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mangrovetechnologies/mangrove-agent/claude-md.svg)](https://agentmods.dev/instructions/mangrovetechnologies/mangrove-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mangrovetechnologies/mangrove-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/mangrovetechnologies/mangrove-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 874 This file is loaded in full into every session.
When invoked 874 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 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 5.1 $0.00874 $0.00874
Opus 5 $0.00437 $0.00437
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00087 $0.00087

Measured 7d ago against content hash bc0351a828c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mangrove-agent CLAUDE.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 7d 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.

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mangrove Agent

A local Mangrove-powered trading bot. Author strategies, backtest, paper-trade, go live when ready. Persona is defined in Project Context + Agent Identity at the bottom of this file.

Architecture

Dual protocol:

  • REST: /api/v1/* (free + auth), /api/x402/* (payment-gated)
  • MCP: /mcp (all tiers via FastMCP)

Three-tier access:

  • Free: no credentials (health, discovery)
  • Auth: API key in X-API-Key header
  • x402: payment or API key bypass (demo route: hello_mangrove)

Service-layer pattern: Routes and MCP tools both call shared services in server/src/services/. Never duplicate business logic.

State ownership: THIS agent owns the tick and the record. APScheduler here fires every strategy evaluation (MangroveAI never schedules for the agent), and the local SQLite (agent-data/agent.db) persists every trade, evaluation, position, and per-strategy execution_state — unconditionally, regardless of evaluation lane. Evaluation itself (signals, sizing, exits) happens in the MangroveAI engine via evaluation_lane: server (default — by-id; engine DB is authoritative for engine position state) or stateless (object-lane; the agent supplies and receives all state, persisted locally and echoed each tick). The engine decides what to trade; the agent decides when to ask, executes, and keeps the books.

Conventions

  • Routes in server/src/api/routes/ -- one file per resource
  • Services in server/src/services/ -- one file per resource, called by both routes and MCP tools
  • MCP tools in server/src/mcp/tools.py -- registered via register_tool()
  • Tests in server/tests/ -- mirror src/
  • Config in server/src/config/ -- per-environment JSON files (no .env)

Full extension workflow: docs/contributing.md.

Rules

  • Trading bot behavior: .claude/rules/trading-bot-workflow.md
  • Wallet handling: .claude/rules/wallet-presentation.md
  • Risk management (engine gates + portfolio kill switch — what happens behind the scenes): .claude/rules/risk-management.md
  • Git workflow: .claude/rules/git-workflow.md

Read the full file on GitHub · 59 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. 7d ago First seen · 59 lines · 874 tokens per session scan A bc0351a828c3

Subscribe to this mod's changes

mangrove-agent CLAUDE.md is an instructions file published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 874 tokens to every session, about $0.0044 per session on Opus 5. 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 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens