agentmods.dev

who_reps-mcp: Instructions file for Claude Code

CLAUDE.md

who_reps-mcp CLAUDE.md is an instructions file for Claude Code from cstillick/who_reps-mcp. It costs 747 tokens per session, scanned A, original, MIT.

A project instruction file for building whoreps-mcp, an MCP server that accepts a U.S. address and returns the elected officials who represent it.

In plain words
What is it for?
Use it to guide work on address-to-district lookups, federal and state representative data, public-data sourcing, SQLite caching, and milestone-based implementation.
Why use it?
It gives the project a standing brief and development rules, including free data sources, partial results when some data is unavailable, caching, and freshness information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

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

not rated 0repo 2mo ago A scan 747 tokens original MIT
View source ↗ cstillick/who_reps-mcp
Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cstillick/who_reps-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cstillick/who_reps-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 747 This file is loaded in full into every session.
When invoked 747 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 $0.00747 $0.00747
Opus 5 $0.00374 $0.00374
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00075 $0.00075

Measured 9d ago against content hash d43b0f58b9f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

who_reps-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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — whoreps-mcp

You are building an MCP server that takes a U.S. address and returns the elected officials for it. This file is your standing brief. Read SPEC.md for the full design and BUILD_PLAN.md for the ordered milestones. Work milestone by milestone; do not skip ahead.

What this project is

A free, open MCP server that replaces the dead Google Civic Representatives API. Address → districts → officials, using only free public data.

Core principles

  • Free inputs only. Every data source must be free (free API key is fine, paid is not). If a source needs payment, find another or note it as out of scope.
  • Graceful degradation. If state-legislator data is missing for a state, still return federal officials and say so. Never fail the whole request because one tier is unavailable.
  • Cache aggressively. Districts for an address rarely change; member rosters change slowly. Cache geocoding and roster lookups locally (SQLite) with sensible TTLs.
  • Be honest about freshness. Every response includes the data source and its as-of date. This is a civic tool; correctness and provenance matter more than cleverness.

Tech stack (default)

  • Python 3.11+, uv for env/deps.
  • Official MCP SDK: mcp package, use FastMCP for ergonomic tool definitions.
  • httpx for HTTP, pydantic for models, sqlite3/sqlite-utils for cache.
  • Transport: stdio by default; expose a --http flag for Streamable HTTP later.
  • (TypeScript alternative is acceptable if the user prefers — the SDK exists — but Python is the default because the data-joining work is simpler here.)

Data sources (all free)

  1. Census Geocoder — https://geocoding.geo.census.gov/geocoder/geographies/onelineaddress returns lat/lon + geographies including the 119th Congressional District and (where available) state legislative districts. No API key.
  2. unitedstates/congress-legislators — the canonical open YAML dataset of current federal legislators (GitHub, public domain). Use this for U.S. Senate + House rather than a live API; it's reliable and key-less. Mirror/cache it.
  3. Congress.gov API (api.congress.gov, free key via api.data.gov) — optional enrichment for member detail/committees.
  4. OpenStates API v3 (https://v3.openstates.org, free key) — state legislators by district. This is the state-tier source.
  5. Governors — small, slow-changing; seed from a maintained open list (e.g., a vendored JSON) and document the refresh process.

Read the full file on GitHub · 43 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 · 43 lines · 747 tokens per session scan A d43b0f58b9f2

Subscribe to this mod's changes

who_reps-mcp CLAUDE.md is an instructions file published in the GitHub repository cstillick/who_reps-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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.

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

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.

github/spec-kit · 7,104 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