turso AGENTS.md

turso AGENTS.md is an instructions file for Codex, OpenCode from tursodatabase/turso. It costs 2,194 tokens per session, scanned A, original, MIT.

Project-wide instructions for developing Turso, a Rust rewrite of SQLite, the database engine used by many applications. They cover building, formatting, linting, running tests, and organizing test suites.

In plain words
What is it for?
Use them to build Turso, run Rust, compatibility, SQL, extension, or MVCC tests, compare behavior with SQLite, format code, and run workspace checks.
Why use it?
They provide the correct commands and test choices for a large multi-package codebase, reducing mistakes caused by using the wrong toolchain or test runner.

Instructions file for CodexOpenCode

About the project

Turso is an in-process SQL database written in Rust that is compatible with SQLite and also accepts PostgreSQL syntax through an experimental frontend. It is for applications and organizations that need an embeddable database engine with support for multiple languages, platforms, and database features. The catalogue entries are skills and instructions for working with Turso.

tursodatabase/turso · 24,093 stars · on GitHub

Install

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.

agentmods
npx agentmods add instructions/tursodatabase/turso/agents-md
Clone the repo
git clone --depth 1 https://github.com/tursodatabase/turso

Made for: Codex, OpenCode.

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.

agentmods badge for turso AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tursodatabase/turso/agents-md.svg)](https://agentmods.dev/instructions/tursodatabase/turso/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tursodatabase/turso/agents-md"><img src="https://agentmods.dev/badge/instructions/tursodatabase/turso/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,194 This file is loaded in full into every session.
When invoked 2,194 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02194 $0.02194
Opus 5 $0.01097 $0.01097
Sonnet 5 $0.00439 $0.00439
Haiku 4.5 $0.00219 $0.00219

Measured 4d ago against content hash c9aa490cf818, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

turso AGENTS.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.

AGENTS.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turso Agent Guidelines

SQLite rewrite in Rust. 40+ crate workspace.

Quick Reference

cargo build                    # build. never build with --release
cargo test                     # rust unit/integration tests
cargo fmt                      # format (required)
cargo clippy --workspace --all-features --all-targets -- --deny=warnings  # lint
cargo run -q --bin tursodb -- -q # run the interactive cli. never run with --release

make test                      # TCL compat + sqlite3 + extensions + MVCC
make test-single TEST=foo.test # single TCL test
make -C sqlite/conformance run-rust ARGS='--snapshot-filter __never__'  # sqltest runner (preferred for new tests)
CI=1 make -C sqlite/conformance run-rust  # use only if snapshot tests are required

scripts/diff.sh "SQL" [label]  # compare sqlite3 vs tursodb output

Testing

Running Tests

  • cargo test - Rust unit and integration tests
  • make test - broad compatibility suite (TCL, sqlite3, extensions, MVCC)
  • make test-single TEST=foo.test - single legacy TCL test
  • make -C sqlite/conformance run-rust ARGS='--snapshot-filter __never__' - preferred .sqltest runner for new coverage
  • CI=1 make -C sqlite/conformance run-rust - only when snapshot tests are required

Test Organization

Default: add coverage to the narrowest existing test harness that can express the bug. Prefer extending an existing test file or directory over creating a new one.

  • sqlite/conformance/sqlite-sqltests/ - preferred for SQL conformance coverage. These tests run the same scenario against both Turso and SQLite, so use them first for parser, planner, executor, and SQL semantics work that fits the .sqltest DSL.
  • tests/integration/ - primary fallback when the behavior cannot be expressed cleanly in .sqltest. Put API-level regressions, multi-connection orchestration, storage assertions, injected failures, timeout behavior, and other Rust-driven scenarios here.
  • sqlite/conformance/upstream/ - imported upstream SQLite golden tests. Do not modify these for Turso behavior changes; use them as fixed compatibility coverage, and only touch them for intentional upstream sync or harness maintenance.
  • postgres/conformance/pg-sqltests/ - .sqltest coverage for the PostgreSQL frontend, run via make -C postgres/conformance run (spawns a tursopg server per test and drives it over the wire protocol). Only assert behavior real PostgreSQL also exhibits, so the corpus stays valid for differential runs.
  • testing/cli_tests/ - CLI-focused Python coverage for shell behavior and end-to-end command workflows.
  • tests/fuzz/ - minimized fuzz regressions and targeted edge cases that are easier to keep as Rust tests.
  • testing/simulator/ and testing/concurrent-simulator/ - deterministic concurrency, scheduling, and failure-injection coverage for state-machine and I/O correctness.
  • testing/differential-oracle/ and testing/stress/ - differential and long-running stress tooling. Use these for deeper investigation or specialized validation, not as the first stop for a focused regression test.

Read the full file on GitHub · 170 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.

  1. 4d ago First seen · 170 lines · 2,194 tokens per session scan A c9aa490cf818

Subscribe to this mod's changes

turso AGENTS.md is an instructions file published in the GitHub repository tursodatabase/turso (24,093 stars, last pushed 5d ago), licensed MIT. It adds 2,194 tokens to every session, about $0.0110 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.