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/uscensusbureau/us-census-bureau-data-api-mcp/copilot-instructionsgit clone --depth 1 https://github.com/uscensusbureau/us-census-bureau-data-api-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/uscensusbureau/us-census-bureau-data-api-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/uscensusbureau/us-census-bureau-data-api-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/uscensusbureau/us-census-bureau-data-api-mcp/copilot-instructions.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 | $0.02107 | $0.02107 |
| Opus 5 | $0.01053 | $0.01053 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
us-census-bureau-data-api-mcp copilot-instructions.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 6d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technology Stack:
- Language: TypeScript (Node.js runtime)
- API: U.S. Census Bureau API
- Database: PostgreSQL (for caching dataset metadata)
- Validation: Zod schemas
- Testing: Vitest
- Build: TypeScript compiler (tsc)
- Package Manager: npm
- Containerization: Docker & Docker Compose
Repository Size: Medium-sized TypeScript project with:
- MCP server application (mcp-server/)
- Database ETL service (mcp-db/)
- Multi-profile Docker Compose setup (dev/test/prod)
- Comprehensive test suite with unit and integration tests
Project Purpose: To enable use of official Census Bureau statistics with AI assistants, leveraging the Model Context Protocol to provide token-optimized data that reduces hallucinations.
Local Development Setup:
The project uses Docker Compose with multiple profiles (dev, test, prod).
Start Development Environment:
docker compose --profile dev up
This starts:
- PostgreSQL database on port 5433
- Runs migrations automatically
- Leaves the dev container running for interactive commands
Run Tests in Development:
docker compose --profile dev exec census-mcp-db-dev-init npm run test
Run Linter in Development:
docker compose --profile dev exec census-mcp-db-dev-init npm run lint
Run Tests (Standalone):
docker compose --profile test up census-mcp-db-test-init
Starts test database and runs the test suite, then exits.
Production Deployment:
docker compose --profile prod up
Starts production services with MCP server on standard PostgreSQL port 5432.
Validation: All validation (build, lint, tests) is handled by CI/GitHub Actions on pull requests.
Important Notes:
- The project is containerized - all services run in Docker
- Development uses port 5433, test uses 5434, prod uses 5432
- Database migrations run automatically on container startup
- The MCP server runs as a containerized service, not standalone
- Focus on writing correct code - let CI handle validation
- If modifying database schema, migrations will auto-run on next startup
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.
- 6d ago First seen · 204 lines · 2,107 tokens per session scan A 8b248f9c4a02
us-census-bureau-data-api-mcp copilot-instructions.md is an instructions file published in the GitHub repository uscensusbureau/us-census-bureau-data-api-mcp (92 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 2,107 tokens to every session, about $0.0105 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 2026-08-30.
Other instructions, from other repositories
tutor-management-app CLAUDE.md
Instructions for t1112000/tutor-management-app, covering claude.md, commands, architecture, auth and page pattern.
mcp-dockhand copilot-instructions.md
Copilot instructions for strausmann/mcp-dockhand, covering copilot instructions — mcp-dockhand, project context, critical: verify against upstream, code review guidelines and security.
better-telegram-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-telegram-mcp, covering agents.md - better-telegram-mcp, build / lint / test commands, run a single test file, run a single test function and mise shortcuts.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
mcp-dockhand gemini-review.instructions.md
Instructions for strausmann/mcp-dockhand, covering gemini code assist review instructions, upstream verification (critical) and code quality checks.
hs-sql-agent AGENTS.md
AGENTS.md instructions for tse-wei-chen/hs-sql-agent, covering agents.md, repo structure, commands, backend and run locally.