Borrowing it
Nothing to install: this file belongs to cstillick/statefinance-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.
curl -O https://raw.githubusercontent.com/cstillick/statefinance-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/cstillick/statefinance-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/cstillick/statefinance-mcp/claude-md)<a href="https://agentmods.dev/instructions/cstillick/statefinance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cstillick/statefinance-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.
<a href="https://agentmods.dev/instructions/cstillick/statefinance-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cstillick/statefinance-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00757 | $0.00757 |
| Opus 5.5 | $0.00303 | $0.00303 |
| Sonnet 5.5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
statefinance-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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — statefinance-mcp
You are building an MCP server that exposes state-level campaign finance data through a common schema, starting with Oklahoma. Read SPEC.md for the design and BUILD_PLAN.md for the ordered milestones. The whole bet of this project is the normalization layer — treat that as the product, not an afterthought.
What this project is
An MCP server answering state campaign-finance questions (donors, expenditures, committees, candidates) from official state disclosure data. Oklahoma first, behind a state-agnostic schema, then more states via adapters.
Core principles
- One schema, many adapters. The core defines
Contribution/Expenditure/Committee/Candidate. Each state implements aStateAdapterthat maps raw state data → that schema. The MCP tools only ever speak the common schema. - Bulk over scraping where possible. Prefer official bulk data exports / data dictionaries over HTML scraping. Document the acquisition method per state.
- Provenance is non-negotiable. Every record links back to the source filing/report and carries an
as_ofdate. This is accountability data; a wrong number is worse than no number. - Ship one state truly well before adding breadth. A correct, complete Oklahoma beats ten half-scraped states.
Tech stack (default)
- Python 3.11+,
uv. - Official MCP SDK (
mcp,FastMCP). httpx,pydanticv2,duckdborsqlitefor the local normalized store,pandas/polarsfor ingestion.- An ingestion CLI (
statefinance ingest ok) separate from the serving layer (the MCP server reads the normalized store). Don't fetch-and-normalize on every tool call.
Data sources
Oklahoma (first adapter)
- Oklahoma Ethics Commission — "Guardian" / Campaign Reporting System:
https://pay.apps.ok.gov/ethics/crs/. Investigate available bulk exports / search endpoints first; only scrape if no export exists, and if you scrape, be polite (rate-limit, cache, identify the client). - Oklahoma reporting thresholds (for validation/context): contributions/expenditures are itemized above small aggregate thresholds; donor records include name, address, occupation, employer.
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 · 44 lines · 757 tokens per session scan A 17e2dbb8a63a
statefinance-mcp CLAUDE.md is an instructions file published in the GitHub repository cstillick/statefinance-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 757 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.
statefinance-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| statefinance-mcp CLAUDE.mdcstillick/statefinance-mcp | Instructions file | 0 | 4mo ago | MIT | A | 757 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |