What is civic-awareness-mcp CLAUDE.md?

A set of developer instructions for a project that provides civic data from the United States. It describes separate tools and databases for federal information, such as Congress and campaign finance, and state information for all states plus Washington, DC.

Use it when developing or maintaining the civic-data servers, their source adapters, command-line entry points, databases, schemas, and data-fetching flow.

It gives contributors shared rules for the project's structure, database setup, API access, request throttling, and cached data. This reduces inconsistent implementation across its parts.

How julianken/civic-awareness-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to julianken/civic-awareness-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/julianken/civic-awareness-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/julianken/civic-awareness-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/julianken/civic-awareness-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/julianken/civic-awareness-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/julianken/civic-awareness-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/julianken/civic-awareness-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/julianken/civic-awareness-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/julianken/civic-awareness-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 748 This file is loaded in full into every session.

When invoked 748 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.

Model	Per session	Once invoked
Fable 5.1	$0.00748	$0.00748
Opus 5.5	$0.00299	$0.00299
Sonnet 5.5	$0.00150	$0.00150
Haiku 4.5	$0.00075	$0.00075

Measured 2mo ago against content hash 729c67f4587a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

civic-awareness-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 2mo 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 · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

civic-awareness-mcp

A marketplace of two MCP servers for US civic data:

federal-mcp (Congress.gov + OpenFEC) — 9 tools
state-mcp (OpenStates, 50 states + DC) — 8 tools

Layout

src/core/ — shared kernel (store, entities, documents, connections, tool_cache, fetch_log, budget, resolution, util)
src/federal/ — Congress.gov + OpenFEC adapters, 9 tools, own schema, own DB at ./data/federal.db
src/state/ — OpenStates adapter, 8 tools, own schema, own DB at ./data/state.db

Each server has its own bin entry, own schemas, own CLI. src/core/ has no source-specific logic.

Key rules

No migrations machinery. Schemas live in src/{core,federal,state}/schema.sql as idempotent CREATE TABLE IF NOT EXISTS. openStore(path, ...schemaPaths) runs them on open. Zero users = no data to preserve.
No phased plans. This is a pre-publish project — no production migration framing, no backwards-compat, no "compile green between commits" discipline for user safety.
Scraping posture: all sources are Tier 1 (sanctioned API, free with key). src/util/http.ts enforces User-Agent, per-host token bucket, backoff, Retry-After.
Hydration flow: tools call withShapedFetch(db, key, ttl, fetchAndWrite, readLocal, peekWaitMs) from src/core/tool_cache.ts. Cache key is (source, endpoint_path, args_hash); freshness rows live in fetch_log. stale_notice fires only when an upstream fetch failed and cached data exists as fallback.
Person entities use EXTERNAL_ID_PATHS in src/core/entities.ts for federal IDs; src/state/entities.ts extends with STATE_EXTERNAL_ID_PATHS for openstates_person.
Code style: no comments explaining WHAT — only WHY when non-obvious. No defensive programming. No backwards-compatibility hacks.
Live API sanity check before merge. Any PR touching src/*/adapters/ or src/*/tools/ must run tsx --env-file=.env.local scripts/sanity-check-tools.ts against real upstreams and show no new errors. MSW-mocked unit tests miss API-contract bugs (datetime format, required query params, upstream filter rules). New tools must add their own case to the sanity script in the same PR. This rule comes from PR #2, which caught 3 such bugs (3/17 = 18%) that passed npm test cleanly.

Read the full file on GitHub · 34 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.

2mo ago First seen · 34 lines · 748 tokens per session scan A 729c67f4587a

Subscribe to this mod's changes

civic-awareness-mcp CLAUDE.md is an instructions file published in the GitHub repository julianken/civic-awareness-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 748 tokens to every session, about $0.0030 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.

Research civic-tech claude congress-gov legislative-data llm-tools mcp

civic-awareness-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
civic-awareness-mcp CLAUDE.mdjulianken/civic-awareness-mcp	Instructions file	1	4mo ago	MIT	A	748	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

civic-awareness-mcp: Instructions file for Claude Code