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/fmeies/etracker-mcp/claude-mdgit clone --depth 1 https://github.com/fmeies/etracker-mcpWrote 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.
[](https://agentmods.dev/instructions/fmeies/etracker-mcp/claude-md)<a href="https://agentmods.dev/instructions/fmeies/etracker-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fmeies/etracker-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01065 | $0.01065 |
| Opus 5 | $0.00532 | $0.00532 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
etracker-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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
etracker MCP Server
Project structure
etracker-mcp/ # repo root — Node.js/TypeScript MCP server
src/
index.ts # Express app, session store, /mcp + /health endpoints
auth.ts # authMiddleware — X-Api-Key + X-ET-Token headers
ratelimit.ts # Three-layer bucket rate limiter (burst / global / per-partner)
cache.ts # In-memory TTL cache (5 min), cache keys scoped per token
analytics-api.ts # etracker Reporting API client (BASE_URL: ws.etracker.com/api/v7)
tools.ts # MCP tool registrations, Zod schemas, column resolution
helm/ # Helm chart for Kubernetes deployment
values.yaml
Dockerfile # Multi-stage build, node:24-alpine
Commands
# Install
npm install
# Dev (tsx, hot-reload via node --import tsx/esm)
npm run dev
# Build
npm run build # tsc → dist/
# Production
npm start # node --env-file=.env dist/index.js
# Docker
docker build -t etracker-mcp .
docker run -p 3000:3000 -e PARTNER_API_KEYS='{"key":"partner-a"}' etracker-mcp
# Helm
helm install etracker-mcp ./helm -f my-values.yaml
Environment variables
| Variable | Required | Description |
|---|---|---|
PARTNER_API_KEYS |
yes | JSON object: {"<key>":"<partner-id>"} — generate keys with openssl rand -hex 32 |
PORT |
no | HTTP port (default: 3000) |
ETRACKER_REPORT_PAGEVIEWS |
no | Override default pageviews report ID (default: EATime) |
ETRACKER_REPORT_CONVERSIONS |
no | Override default conversions report ID (default: EAConversions) |
ETRACKER_REPORT_AD |
no | Override default ad report ID (default: EAMarketing) |
Copy .env.example to .env for local development. The etracker token is not stored in env — partners pass it per request via X-ET-Token.
Authentication model
Every request to /mcp requires two headers:
X-Api-Key— MCP server access key (validated againstPARTNER_API_KEYS, resolves to apartnerIdused for rate limiting)X-ET-Token— etracker account token (forwarded directly to the etracker API; never stored server-side)
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.
- 4d ago First seen · 98 lines · 1,065 tokens per session scan A e7df08cdb3af
etracker-mcp CLAUDE.md is an instructions file published in the GitHub repository fmeies/etracker-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,065 tokens to every session, about $0.0053 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.