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/everstake/mcp/claude-mdgit clone --depth 1 https://github.com/everstake/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/everstake/mcp/claude-md)<a href="https://agentmods.dev/instructions/everstake/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/everstake/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 | $0.01727 | $0.01727 |
| Opus 5 | $0.00864 | $0.00864 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
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 3d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Everstake MCP Server — Session Context
Project
MCP server exposing Everstake data to AI agents. Built in Go using the official modelcontextprotocol/go-sdk.
Repo root: mcp-server module
Entry point: cmd/mcp_server/main.go
Stack
| Concern | Choice |
|---|---|
| MCP SDK | github.com/modelcontextprotocol/go-sdk v1.4.1 |
| HTTP router | github.com/gin-gonic/gin v1.10.0 |
| MCP transport | Streamable HTTP (/ via NewStreamableHTTPHandler) or stdio (StdioTransport), selected by MCP_TRANSPORT |
| Config | github.com/caarlos0/env — env vars, no file |
| Cache | github.com/patrickmn/go-cache — in-memory, 10 min TTL |
| Logging | github.com/sirupsen/logrus |
| Go version | 1.26.1 |
Structure
cmd/mcp_server/main.go signal handling, wires deps, starts server
internal/
config/
service_config.go ServiceConfig{Port, DashboardUrl, Transport} via caarlos0/env
mcp_config.go ToolsConfig, custom UnmarshalYAML, LoadMCPConfig
config_unmarshal_test.go tests for YAML unmarshaling
server/
server.go Gin router, /health, mounts MCP handler, graceful shutdown
mcp/
server.go MCPServer struct, New(), Handler() (http), RunStdio() (stdio), tool registration
dashboard.go GetUptimeMetrics, GetChains handlers (live API + cache)
utils.go newTextResult(), newJsonResult(), staticTextTool(), ErrFailedToFetchDashboard
middleware/
ratelimit.go rate limiting middleware
pkg/
everstake/dashboard/ HTTP client for dashboard-api.everstake.com
dashboard.go Dashboard client, base HTTP methods
chains.go Chain types and API endpoints
datafeed.go Data feed types and API endpoints
leads.go Leads types and API endpoints
log/
log.go logrus wrapper
mcp.go embed tools.yaml, Version, ServiceName, DashboardCacheTtl consts
tools.yaml tool definitions (name derived from map key, not field)
Dockerfile multi-stage, golang:1.26.1-alpine builder + alpine:3.21 runtime
Makefile build automation (lint)
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.
- 3d ago First seen · 159 lines · 1,727 tokens per session scan A 6e56af68c1a6
mcp CLAUDE.md is an instructions file published in the GitHub repository everstake/mcp (1 stars, last pushed 9d ago), licensed BSD-3-Clause. It adds 1,727 tokens to every session, about $0.0086 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.