agentmods.dev

sql-benchmarks-dagster: Instructions file for Codex

AGENTS.md

sql-benchmarks-dagster AGENTS.md is an instructions file for Codex, OpenCode from rctruta/sql-benchmarks-dagster. It costs 2,798 tokens per session, scanned A, original, Apache-2.0.

Instructions for running repeatable SQL performance experiments in a benchmarking laboratory, using files, an HTTP API, or MCP tools.

In plain words
What is it for?
They are for submitting benchmark configurations, reading result capsules, comparing database engines, and requesting engine recommendations.
Why use it?
They let an agent test a performance claim and verify the recorded result instead of relying on an untested assumption.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code.

This is rctruta/sql-benchmarks-dagster's own configuration. It tells Codex and OpenCode how to work on sql-benchmarks-dagster itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sql-benchmarks-dagster configures →

not rated 3repo changed 9d ago A scan 2,798 tokens original Apache-2.0
View source ↗ rctruta/sql-benchmarks-dagster
Reuse

Borrowing it

Nothing to install: this file belongs to rctruta/sql-benchmarks-dagster. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rctruta/sql-benchmarks-dagster/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rctruta/sql-benchmarks-dagster

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 sql-benchmarks-dagster AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rctruta/sql-benchmarks-dagster/agents-md/github.svg)](https://agentmods.dev/instructions/rctruta/sql-benchmarks-dagster/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rctruta/sql-benchmarks-dagster/agents-md"><img src="https://agentmods.dev/badge/instructions/rctruta/sql-benchmarks-dagster/agents-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.

agentmods 80×15 button for sql-benchmarks-dagster AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rctruta/sql-benchmarks-dagster/agents-md"><img src="https://agentmods.dev/badge/instructions/rctruta/sql-benchmarks-dagster/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,798 This file is loaded in full into every session.
When invoked 2,798 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02798 $0.02798
Opus 5.5 $0.01119 $0.01119
Sonnet 5.5 $0.00560 $0.00560
Haiku 4.5 $0.00280 $0.00280

Measured 9d ago against content hash 740f5e1dfe3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sql-benchmarks-dagster 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 9d 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 · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Benchmarking Protocol

Specification for AI agents and orchestrators interacting with the SQL Benchmarking Laboratory.

The lab is an empirical benchmarking harness: every experiment is identified by a content-addressed hash, every result is a verifiable capsule, and every interface below is machine-first. An agent can verify a performance hypothesis here instead of asserting it.

Standard Engineering Practices (No One-Offs)

  • All code, scripts, linters, and configurations must adhere to standard engineering practices.
  • Do not create ad-hoc, brittle single-use scripts, custom regex parsers, or bespoke governance mechanisms where industry-standard tooling exists.
  • Private material stays outside the repository. Personal notes, summaries of chat conversations, local machine paths, and unpublished work are never copied in, referenced by absolute path, or quoted in code, comments, tests, commit messages or PR text. Code that needs private data reads its location from an environment variable.

Documentation Triggers (When to Update README)

Do NOT update the README for internal bug fixes, refactorings, or minor code edits. Review and update README and agent instructions ONLY when a change crosses an external boundary:

  1. CLI / Entrypoints: A command, CLI flag, or runner script is added, renamed, or removed.
  2. Dependencies & Toolchain: A dependency, interpreter version, or external tool requirement is changed in pyproject.toml.
  3. Environment & Configuration: A new environment variable, configuration table, or setup prerequisite is introduced.
  4. Repository Layout: A top-level directory or primary data pipeline is added, moved, or removed. If none of these boundaries was crossed, leave the README untouched.

Four ways in

  1. Filesystem + CLI (zero infrastructure): write a YAML config, run it, read the capsule.
  2. REST API (python serve.py, then http://localhost:8000/docs): catalog, results, cross-engine comparison, engine recommendation, async experiment submission.
  3. MCP server, this checkout (python mcp_server.py): the same capabilities as native tools for MCP-capable agents. Requires the REST API to be running — it is an HTTP client against SB_API_BASE, default http://localhost:8000. (Note: This repository is natively Agent-Ready. It ships a claude.json configuration, meaning Claude Code will automatically mount the MCP server upon entering the directory.)
  4. MCP server, installed (uvx --from sqlbenchdag sqlbench-mcp): the published entry point, sql_benchmarks.mcp.server. No REST API and no setup — it reads the committed capsules directly, so a cold install answers questions about pre-computed results in one command. This is the path anyone outside this repository uses; the two servers are separate code with separate requirements.

Read the full file on GitHub · 220 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. 9d ago Changed · -1 tokens per session 740f5e1dfe3d
  2. 12d ago Changed · +4 lines · -14 tokens per session 95111fb51f12
  3. 18d ago Changed · +60 lines · +862 tokens per session d8a4ac89664b
  4. 20d ago Changed · +6 lines · +121 tokens per session b38d4e205677
  5. 2mo ago First seen · 150 lines · 1,830 tokens per session scan A 7327623f4431

Subscribe to this mod's changes

sql-benchmarks-dagster AGENTS.md is an instructions file published in the GitHub repository rctruta/sql-benchmarks-dagster (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 2,798 tokens to every session, about $0.0112 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.

Analytics and metricsDatabasesbenchmarksdagsterdocker-composeduckdbpostgresqlsql
Related

sql-benchmarks-dagster AGENTS.md compared with instructions from other repositories

sql-benchmarks-dagster AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sql-benchmarks-dagster AGENTS.mdrctruta/sql-benchmarks-dagsterInstructions file39d agoApache-2.0A2,798Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode