Borrowing it
Nothing to install: this file belongs to clement-tourriere/dbcrust. 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/clement-tourriere/dbcrust/main/CLAUDE.mdgit clone --depth 1 https://github.com/clement-tourriere/dbcrustWrote 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/clement-tourriere/dbcrust/claude-md)<a href="https://agentmods.dev/instructions/clement-tourriere/dbcrust/claude-md"><img src="https://agentmods.dev/badge/instructions/clement-tourriere/dbcrust/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/clement-tourriere/dbcrust/claude-md"><img src="https://agentmods.dev/badge/instructions/clement-tourriere/dbcrust/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 | $0.02336 | $0.02336 |
| Opus 5 | $0.01168 | $0.01168 |
| Sonnet 5 | $0.00467 | $0.00467 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
dbcrust 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 yesterday.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
DBCrust — high-performance multi-engine interactive client in Rust with Python bindings. Supports PostgreSQL, MySQL, SQLite, MongoDB, ClickHouse, Elasticsearch, White Dragon, and file formats (Parquet, CSV, JSON) via Apache DataFusion.
Build Commands
mise.toml requires mise 2026.8.16+ and routes Cargo through the pinned Mr Boxington build cache. Run mise install once; use mise run tasks (or an activated mise shell) so Cargo is wrapped. Diagnose cache setup with mbx doctor.
mise install
mise run build:dev # dev build
mise run build # release build
mise run install # install dbcrust + dbc into ~/.cargo/bin
mise run test # run tests
cargo test -- --nocapture # tests with output
cargo run -- postgres://localhost/test # run CLI directly
# Python bindings
mise run py:dev # maturin dev build
mise run py:build # wheel
# GUI (Tauri)
mise run gui:install && mise run gui:build
Module Map
| File | Purpose |
|---|---|
src/main.rs |
Entry point, Tokio runtime, CLI orchestration |
src/lib.rs |
PyO3 bindings (PyDatabase, PyConfig, run_cli_loop) |
src/commands.rs |
Enum-based command system — all \cmd logic lives here |
src/cli.rs |
Arg parsing via usage-rs derive (jdx/usage) — private Root wraps public Args; one-shot flags (-c/-f, -o/--format, --read-only, --no-input); OutputFormat/OneShotSource/ParseExit live here; hidden __complete_word__/__usage_spec__ endpoints answered in parse_from_argv |
src/shell_completion.rs |
Rust-side URL completer (complete_connection_url: schemes, sessions, docker, files) + completion-script generation (usage scripts call the binary back at Tab time) |
src/safety.rs |
Read-only statement classification — --read-only guard + AI agent guard share it |
src/agent_guide.md |
Embedded dbcrust agents guide (the one-shot contract for AI coding agents) |
src/ai/ |
AI assistant (?? text-to-SQL, \ai) — multi-provider via genai |
src/update.rs |
--update: install-channel detection + GitHub release check |
src/config.rs |
TOML config, save_with_documentation must be updated for new fields |
src/config_editor.rs |
Schema-driven \config menu/get/set + SSH tunnel manager (dbcrust config CLI) |
src/prompt.rs |
Reedline interactive REPL |
src/completion.rs |
SQL autocomplete with metadata caching |
src/format.rs |
Output formatting (table, expanded, CSV, JSON, JSONL) — render_query_results is the dispatch |
src/database.rs |
DatabaseClient + MetadataProvider traits |
src/database_postgresql.rs |
PG implementation (format_postgresql_value ~line 1390) |
src/database_datafusion.rs |
File format queries (Parquet, CSV, JSON) |
src/database_white_dragon.rs |
White Dragon SQL/qualifier HTTP adapter with generic WDSP schema introspection |
src/ssh_tunnel.rs |
SSH tunnel management |
src/vault_client.rs |
HashiCorp Vault credentials |
src/named_queries.rs |
Parameterized queries ($1, $*, $@) |
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.
- yesterday Changed · +11 lines · +403 tokens per session b9590e726504
- 10d ago First seen · 152 lines · 1,933 tokens per session scan A 6a440a7288aa
dbcrust CLAUDE.md is an instructions file published in the GitHub repository clement-tourriere/dbcrust (92 stars, last pushed yesterday), licensed MIT. It adds 2,336 tokens to every session, about $0.0117 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
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.