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/faucetdb/faucet/claude-mdgit clone --depth 1 https://github.com/faucetdb/faucetWrote 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/faucetdb/faucet/claude-md)<a href="https://agentmods.dev/instructions/faucetdb/faucet/claude-md"><img src="https://agentmods.dev/badge/instructions/faucetdb/faucet/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 | $0.00562 | $0.00562 |
| Opus 5 | $0.00281 | $0.00281 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
faucet 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 4d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Faucet - CLAUDE.md
Instructions for AI assistants working on this codebase.
What Is This?
Faucet is an open-source Go application that turns any SQL database into a secure REST API. Single binary, zero configuration, built-in MCP server for AI agents.
Architecture
- Language: Go 1.24+
- HTTP Router: Chi (
go-chi/chi/v5) - DB Access:
jmoiron/sqlxoverdatabase/sql - CLI: Cobra + Viper
- Config Storage: Embedded SQLite (
modernc.org/sqlite, pure Go) - Frontend: Preact + Vite + Tailwind, embedded via
go:embed
Project Structure
cmd/faucet/ - CLI entry point and Cobra commands
internal/
server/ - HTTP server, Chi router, middleware
handler/ - HTTP request handlers
service/ - Business logic layer
connector/ - Database connector interface + implementations
postgres/ - PostgreSQL connector
mysql/ - MySQL connector
mssql/ - SQL Server connector
snowflake/ - Snowflake connector
query/ - Filter parser, query builder utilities
openapi/ - OpenAPI 3.1 spec generator
mcp/ - MCP server implementation
config/ - SQLite config store, YAML config
model/ - Data models (shared types)
ui/dist/ - Embedded frontend assets
ui/ - Frontend source (Preact)
Key Commands
make build # Build binary (UI + Go)
make build-go # Build Go binary only
make test # Run all tests
make dev # Run in dev mode
make lint # Run linter
Conventions
- All filter values MUST be parameterized (never string-interpolated) to prevent SQL injection
- Every database connector implements the
connector.Connectorinterface - Response format:
{"resource": [...], "meta": {...}}for lists - Error format:
{"error": {"code": N, "message": "...", "context": {...}}} - API keys are SHA-256 hashed, admin passwords are bcrypt hashed
- All table/column names must pass
query.ValidateIdentifier()
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.
- 4d ago First seen · 70 lines · 562 tokens per session scan A 562b7e3292ac
faucet CLAUDE.md is an instructions file published in the GitHub repository faucetdb/faucet (109 stars, last pushed today), licensed MIT. It adds 562 tokens to every session, about $0.0028 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
prest copilot-instructions.md
Copilot instructions for prest/prest, covering copilot instructions for prest go backend, project scope, core engineering principles, solid principles for go and s — single responsibility.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
gorest CLAUDE.md
Claude Code instructions for pilinux/gorest, covering claude.md, authoritative references, files to never read or modify, common commands and architecture (the big picture).
GoSQLX CLAUDE.md
Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.
ronykit AGENTS.md
AGENTS.md instructions for clubpay/ronykit, covering agents.md, ai assistants, context map, contracts & schemas and project overview.
sonicjs CLAUDE.md
Claude Code instructions for SonicJs-Org/sonicjs, covering sonicjs ai development guidelines, core technology stack, workspace boundary (conductor), architecture direction: document model (authoritative) and the 5 document tables (migration 0002documents.sql).