agentmods.dev

mcp-redtrack: Instructions file for Claude Code

CLAUDE.md

mcp-redtrack CLAUDE.md is an instructions file for Claude Code from pijusz/mcp-redtrack. It costs 638 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that connects to RedTrack, an affiliate-marketing tracking service.

In plain words
What is it for?
Use them when developing or testing tools for campaigns, clicks, conversions, reports, and other RedTrack entities.
Why use it?
They explain the available API operations, authentication, testing, and request-handling rules in one place.

Instructions file for Claude Code

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

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

not rated 1repo changed 14d ago A scan 638 tokens original MIT
View source ↗ pijusz/mcp-redtrack
Reuse

Borrowing it

Nothing to install: this file belongs to pijusz/mcp-redtrack. 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/pijusz/mcp-redtrack/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pijusz/mcp-redtrack

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 mcp-redtrack CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pijusz/mcp-redtrack/claude-md"><img src="https://agentmods.dev/badge/instructions/pijusz/mcp-redtrack/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 638 This file is loaded in full into every session.
When invoked 638 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 $0.00638 $0.00638
Opus 5.5 $0.00255 $0.00255
Sonnet 5.5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 14d ago against content hash b9fc01b396d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-redtrack 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 14d 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-redtrack

MCP server for the RedTrack affiliate tracking API.

Quick reference

Item Value
Runtime Bun (dev) / Node 18+ (npm)
Entry src/index.ts
Build bun run build (binary) or bun run build:npm (Node)
Test bun test
Lint biome check .
API base https://api.redtrack.io
Auth api_key query parameter on every request
Swagger swagger.json (local copy)

Key patterns

  • MCP response format: always { content: [{ type: "text", text: string }] }
  • fetchWithRetry: exponential backoff on 429/5xx, 30s timeout, 2 retries
  • Date defaults: log tools default to last 7 days if no date range provided
  • Config: Zod-validated env, lazy singleton, .env file support
  • Logging: all logs to stderr via log.info/warn/error/debug

Tools (18 total, all read-only via readTool)

Campaigns (3)

  • get_campaigns — list with filters and optional stats
  • get_campaign — single campaign by ID
  • get_campaigns_v2 — v2 endpoint

Logs (2)

  • get_clicks — click-level log (GET /tracks)
  • get_conversions — conversion-level log

Reports (1)

  • get_report — aggregated stats grouped by dimension

Entities (12)

  • get_offers / get_offer — offers
  • get_sources / get_source — traffic sources
  • get_networks / get_network — affiliate networks
  • get_landings / get_landing — landing pages
  • get_streams, get_domains — streams, tracking domains
  • get_dictionary — reference lists (countries, timezones, browsers, ...)
  • get_settings — account settings

API quirks (verified live)

  • per is ignored unless page is sent; buildUrl defaults page=1 when only per is given
  • /report?direction takes asc/desc (swagger wrongly says integer)
  • Rate limit is tight: ~5 rapid calls trigger HTTP 429

Adding new tools

  1. Create src/tools/newmodule.ts with registerXTools(server) export, registering via readTool/writeTool from src/utils/register-tool.ts (sets MCP annotations)
  2. Add Zod schemas for all parameters
  3. Call API via services/redtrack-api.ts
  4. Format output with formatTable() or JSON
  5. Register in src/tools/index.ts and update the tool count in tests/server.test.ts

Read the full file on GitHub · 62 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. 14d ago Changed · +8 lines · +162 tokens per session b9fc01b396d2
  2. 2mo ago First seen · 54 lines · 476 tokens per session scan A d9ace8b86308

Subscribe to this mod's changes

mcp-redtrack CLAUDE.md is an instructions file published in the GitHub repository pijusz/mcp-redtrack (1 stars, last pushed 15d ago), licensed MIT. It adds 638 tokens to every session, about $0.0026 per session on Opus 5.5. 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

mcp-redtrack CLAUDE.md compared with instructions from other repositories

mcp-redtrack CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-redtrack CLAUDE.mdpijusz/mcp-redtrackInstructions file115d agoMITA638Claude Code
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