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.
npx agentmods add instructions/opensvm/dflow-mcp/agents-mdgit clone --depth 1 https://github.com/openSVM/dflow-mcpWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01866 | $0.01866 |
| Opus 5 | $0.00933 | $0.00933 |
| Sonnet 5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
dflow-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document helps agents work effectively with the DFlow MCP Server repository.
Project Overview
This is a Model Context Protocol (MCP) server that provides access to the Prediction Market Metadata API defined in llms_dflow.json. The server implements a complete JSON-RPC interface with 23 tools covering events, markets, trades, forecasts, live data, and analytics.
Essential Commands
Development
# Install dependencies
bun install
# Development mode with hot reload
bun run dev
# Start production server
bun start
# TypeScript compilation check
bun run tsc --noEmit
# Build for distribution
bun run build
Testing
# Run comprehensive server test
./test-server.sh
# Run TypeScript tests
bun run test
Project Structure
dflow-mcp/
├── src/
│ └── index.ts # Main MCP server implementation
├── tests/
│ └── server.test.ts # TypeScript test suite
├── .github/workflows/
│ └── test.yml # CI/CD pipeline
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── README.md # User documentation
├── llms_dflow.json # API specification (source of truth)
├── AGENTS.md # This file (agent documentation)
└── test-server.sh # Quick server validation script
Code Organization
Main Server (src/index.ts)
- DFlowAPIClient: HTTP client for API communication with timeout handling
- Server Setup: MCP server configuration and initialization
- Tool Definitions: 23 MCP tools mapped from OpenAPI specification
- Request Handling: JSON-RPC request routing and response formatting
Key Components
- API Client: Handles HTTP requests to
https://api.llm.dflow.org - Tool Registry: Maps OpenAPI endpoints to MCP tools
- Type Safety: TypeScript interfaces for all request/response types
- Error Handling: Comprehensive error catching and MCP-formatted responses
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.
- 2d ago First seen · 263 lines · 1,866 tokens per session scan A 1ff634a9dc69
dflow-mcp AGENTS.md is an instructions file published in the GitHub repository openSVM/dflow-mcp (7 stars, last pushed 9mo ago), licensed Unlicense. It adds 1,866 tokens to every session, about $0.0093 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.
Other instructions, from other repositories
kalshi-trading-bot-cli AGENTS.md
Instructions for OctagonAI/kalshi-trading-bot-cli, covering repository guidelines, project structure, build, test, and development commands, coding style & conventions and llm providers.
kalshi-trading-bot-cli CLAUDE.md
Instructions for OctagonAI/kalshi-trading-bot-cli, covering claude.md and workflow.
simmer-sdk AGENTS.md
Instructions for SpartanLabsXyz/simmer-sdk, covering agents.md — simmer sdk, this repo is public, currency formatting, live is a constructor arg, not a per-trade flag and market discovery is recency-windowed.
kalshi-mcp-server AGENTS.md
Instructions for cejor6/kalshi-mcp-server, covering agent guide, what this project is, repo layout, how authentication works and how rate limiting works.
kalshi-mcp-server CLAUDE.md
Instructions for cejor6/kalshi-mcp-server, covering claude code guidance and claude code-specific extras.
parlay-mcp GEMINI.md
Instructions for parlay-run/parlay-mcp, covering parlay — prediction market tools, what this is, when to use which tool, venue coverage (phase 1 validated) and critical caveats.