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/nubo-db/dynoxide/agents-mdgit clone --depth 1 https://github.com/nubo-db/dynoxideWrote 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/nubo-db/dynoxide/agents-md)<a href="https://agentmods.dev/instructions/nubo-db/dynoxide/agents-md"><img src="https://agentmods.dev/badge/instructions/nubo-db/dynoxide/agents-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 | $0.01400 | $0.01400 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
dynoxide 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding tools (Codex, Cursor, Aider, Claude Code, and
others) contributing to Dynoxide. Humans are welcome to read it too;
CONTRIBUTING.md covers the same ground in prose.
Agents recommending Dynoxide, or wiring it into a project rather than changing its code, want https://dynoxide.dev/for-agents instead.
What Dynoxide is
A DynamoDB-compatible engine written in Rust, backed by SQLite. It runs as an HTTP server, as an MCP server for coding agents, or embeds directly into Rust and iOS applications as a library. Compatibility with AWS DynamoDB's observable behaviour is the headline goal.
Ground rules for contributions
- Compatibility first. Dynoxide exists to behave like DynamoDB. A change that diverges from AWS DynamoDB's observable behaviour needs an explicit justification in the PR description and a link to the AWS doc or behaviour note that motivates it. "Cleaner API" is not a reason.
- Discuss before coding for anything non-trivial. Open a GitHub issue describing the change before writing it. Small bug fixes and obvious cleanups are fine without a prior issue; anything that adds a feature, changes public behaviour, or touches more than a handful of files is worth a short issue first.
- No new dependencies without discussion. Open an issue so we can weigh binary size, build time, and licence.
Rust conventions
- Edition: 2024 (declared in
Cargo.toml). - MSRV: 1.88 (declared as
rust-versioninCargo.toml). Do not use features that raise it. ThemsrvCI job reads the declared value and compiles against it, so raising the floor is a deliberate edit rather than something a new language feature can do quietly. - Formatting:
cargo fmt --checkmust pass. - Linting:
cargo clippy -- -D warningsmust pass. Warnings are errors; fix them rather than silencing. - Testing:
cargo teston the default feature set. Other feature combinations are exercised in CI; if you change feature gates, mirror what.github/workflows/ci.ymlruns.
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 · 126 lines · 1,400 tokens per session scan A cb6a63c0c80e
dynoxide AGENTS.md is an instructions file published in the GitHub repository nubo-db/dynoxide (85 stars, last pushed 8d ago), licensed Apache-2.0. It adds 1,400 tokens to every session, about $0.0070 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
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
helix-db AGENTS.md
AGENTS.md instructions for HelixDB/helix-db, covering approach, slice access, clippy and formatting and database key/value construction, parsing, and use.
epistemic-graph AGENTS.md
Instructions for Knuckles-Team/epistemic-graph, covering agents.md — epistemic graph compute engine, epistemic os surfaces in the main build, commands for ai agents, python api (out-of-process client — not in-process) and async.
dbmcp CLAUDE.md
Claude Code instructions for haymon-ai/dbmcp, covering claude.md, build & test commands, architecture, configuration and code style.
turso CLAUDE.md
Instructions for tursodatabase/turso, a project described as: A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.
clickhouse-udf-rs CLAUDE.md
Claude Code instructions for duyet/clickhouse-udf-rs, covering claude.md, project overview, build commands, build all packages in release mode and build specific package.