prediction-mcp: Instructions file for Claude Code

CLAUDE.md

prediction-mcp CLAUDE.md is an instructions file for Claude Code from shaanmajid/prediction-mcp. It costs 1,605 tokens per session, scanned A, original, MIT.

Contributor instructions for prediction-mcp, an MCP server that accesses Kalshi and Polymarket prediction-market data.

In plain words
What is it for?
Use them to develop or test prediction-mcp, check its API integrations, run its tests, and verify changed tools directly.
Why use it?
They explain how to work with the platform APIs, test changes, and handle the fact that server changes require restarting the coding-agent session.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is shaanmajid/prediction-mcp's own configuration. It tells Claude Code how to work on prediction-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 prediction-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shaanmajid/prediction-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/shaanmajid/prediction-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shaanmajid/prediction-mcp

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 prediction-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shaanmajid/prediction-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/shaanmajid/prediction-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shaanmajid/prediction-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shaanmajid/prediction-mcp/claude-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 prediction-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shaanmajid/prediction-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shaanmajid/prediction-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,605 This file is loaded in full into every session.
When invoked 1,605 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 $0.01605 $0.01605
Opus 5 $0.00803 $0.00803
Sonnet 5 $0.00321 $0.00321
Haiku 4.5 $0.00161 $0.00161

Measured 9d ago against content hash 988532e92fef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prediction-mcp 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 9d 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 · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prediction Markets MCP Server

For users: Install via npm with npx prediction-mcp. See README.md for setup instructions.

This file is for contributors developing the server itself.

API Reference

Always consult these docs when working with platform APIs:

Platform Documentation
Kalshi https://docs.kalshi.com/api-reference
Polymarket Gamma https://docs.polymarket.com/developers/gamma-markets-api/overview
Polymarket CLOB https://docs.polymarket.com/#clob-api
MCP Protocol https://modelcontextprotocol.io/specification

Development Workflow

Testing Changes

All functional changes must be tested by invoking the MCP tools directly.

  1. Run bun run scripts/bootstrap.ts to register your worktree's server in .mcp.json
  2. Exit and resume your Claude Code session — the server won't reload until restart
  3. Invoke the tools you modified to verify they work correctly
  4. Run bun test to ensure all tests pass

Critical: Session Restart Required

MCP servers are loaded when the Claude Code session starts. If you:

  • Add MCP config for the first time
  • Update server code and need to test changes
  • Modify tool definitions or handlers

You must exit and resume the session to load the updated server.

The bootstrap script reminds you of this, but it's easy to forget when iterating on code changes.

Worktree Setup

Each git worktree needs its own .mcp.json pointing to its index.ts:

cd /path/to/your-worktree
bun install
bun run scripts/bootstrap.ts
# Exit and resume Claude Code session

Architecture

index.ts                    Server entry point
src/
  clients/
    kalshi.ts               Kalshi SDK wrapper with bulk fetch
    polymarket.ts           Gamma API (REST) + CLOB SDK
  search/
    index.ts                Exports for search module
    cache.ts                Kalshi tokenized search with scoring
    service.ts              Kalshi search: lazy init, refresh
    polymarket-cache.ts     Polymarket tokenized search cache
    polymarket-service.ts   Polymarket search service
    scoring.ts              Shared scoring utilities
  env.ts                    Environment config (Zod + t3-env)
  logger.ts                 Pino logger configuration
  tools.ts                  MCP tool handlers
  validation.ts             Zod v4 schemas (generate JSON Schema)
scripts/
  bootstrap.ts              Register server with MCP clients
  docs.ts                   Generate/check docs (subcommands)
docs/                       Auto-generated—do not edit

Read the full file on GitHub · 207 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. 9d ago First seen · 207 lines · 1,605 tokens per session scan A 988532e92fef

Subscribe to this mod's changes

prediction-mcp CLAUDE.md is an instructions file published in the GitHub repository shaanmajid/prediction-mcp (12 stars, last pushed 3mo ago), licensed MIT. It adds 1,605 tokens to every session, about $0.0080 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 2026-08-30.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens