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/kovashikawa/bls_mcp/claude-mdgit clone --depth 1 https://github.com/kovashikawa/bls_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/kovashikawa/bls_mcp/claude-md)<a href="https://agentmods.dev/instructions/kovashikawa/bls_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kovashikawa/bls_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 5.1 | $0.01774 | $0.01774 |
| Opus 5 | $0.00887 | $0.00887 |
| Sonnet 5 | $0.00355 | $0.00355 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
bls_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 5d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
A standalone Model Context Protocol (MCP) server for Bureau of Labor Statistics (BLS) data. Built with the official mcp Python SDK, this server provides tools for accessing CPI (Consumer Price Index) data through mock data fixtures. Currently in Phase 2 with visualization capabilities.
Key Architecture
MCP Server Design
The server uses the official MCP SDK (not FastMCP) with:
- stdio transport for local testing and Claude Desktop integration
- SSE transport for remote access via ngrok
- Tool-based architecture where each tool inherits from
BaseTool - Mock data provider that loads from JSON fixtures on-demand with lazy loading
Data Flow
MCP Client (Claude Desktop, etc.)
↓ JSON-RPC over stdio/SSE
BLSMCPServer (server.py)
↓ tool routing
Tool classes (get_series.py, plot_series.py, etc.)
↓ async data fetching
MockDataProvider (mock_data.py)
↓ lazy load from fixtures/
JSON fixtures (cpi_series.json, historical_data.json)
Tool Pattern
All tools follow this pattern:
- Inherit from
BaseToolabstract class - Define
name,description, andinput_schema(Pydantic model) - Implement async
execute(arguments)method - Return structured dict with
statusand data/error - Input validation happens via Pydantic before execution
Critical Implementation Details
- plot_series returns data, not images: The tool returns structured JSON data suitable for client-side plotting, not pre-rendered images. This is more stable across different LLM clients (ChatGPT, Claude, etc.).
- Lazy data loading: Mock data loads from JSON fixtures only when first accessed and caches in memory
- Multiple server entry points:
bls-mcp(stdio) andbls-mcp-ngrok(SSE) defined in pyproject.toml - No matplotlib dependency: The plot_series tool no longer requires matplotlib - it just formats and returns data
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.
- 5d ago First seen · 239 lines · 1,774 tokens per session scan A c13076c15fe5
bls_mcp CLAUDE.md is an instructions file published in the GitHub repository kovashikawa/bls_mcp (0 stars, last pushed 10mo ago), licensed MIT. It adds 1,774 tokens to every session, about $0.0089 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
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
ken CLAUDE.md
Claude Code instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
ZipAI CLAUDE.md
Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
gpu-ai-skills CLAUDE.md
Claude Code instructions for intel/gpu-ai-skills, covering claude.md, what this repository is, repository structure, commands and validation (required before any skill change).
TreeSkill CLAUDE.md
Instructions for JimmyMa99/TreeSkill, covering claude.md, project overview, commands, install and run tests.