What is ai_clients_dart AGENTS.md?

Repository-specific development rules for a collection of Dart and Flutter client libraries for AI services such as OpenAI, Anthropic, Gemini, Mistral, and Ollama. The repository is a monorepo, meaning several related packages are maintained together in one workspace.

Use them when developing or reviewing packages in the Dart AI client repository. They cover workspace setup, dependency linking, formatting, automatic fixes, and static analysis.

They explain how to initialize the shared workspace and keep code quality checks consistent across all packages. They also prescribe the order for formatting, automatic fixes, and analysis so errors are easier to review.

How davidmigloz/ai_clients_dart configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to davidmigloz/ai_clients_dart. 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/davidmigloz/ai_clients_dart/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/davidmigloz/ai_clients_dart

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/davidmigloz/ai_clients_dart/agents-md/github.svg)](https://agentmods.dev/instructions/davidmigloz/ai_clients_dart/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/davidmigloz/ai_clients_dart/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmigloz/ai_clients_dart/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/davidmigloz/ai_clients_dart/agents-md"><img src="https://agentmods.dev/badge/instructions/davidmigloz/ai_clients_dart/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,178 This file is loaded in full into every session.

When invoked 1,178 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.

Model	Per session	Once invoked
Fable 5.1	$0.01178	$0.01178
Opus 5	$0.00589	$0.00589
Sonnet 5	$0.00236	$0.00236
Haiku 4.5	$0.00118	$0.00118

Measured 9d ago against content hash 0cd294d8fc94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai_clients_dart 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 · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Clients Dart

A collection of Dart client libraries for popular AI APIs. Provides type-safe, well-documented, and idiomatic interfaces to OpenAI, Anthropic, Google AI (Gemini), Mistral, Ollama, and other providers. Ready for Dart and Flutter.

Repository Structure

This repository uses a Pub Workspace defined at the root level (/pubspec.yaml).

ai_clients_dart/
├── packages/             # Client packages
├── pubspec.yaml          # Workspace root, centralized dependencies, melos config
└── analysis_options.yaml # Dart linting rules

Development Commands

Dart Monorepo Setup

# Workspace initialization (CLI required for melos) - run from repository root
melos bootstrap   # Install dependencies and link local packages

Code Quality

Use CLI commands with quiet flags to minimize context noise. Run in this order — dart fix auto-fixes analyzer issues before dart analyze surfaces only those needing manual attention:

dart format --show=none --summary=line .   # Format; only prints summary
dart fix --apply                           # Auto-fix analyzer issues with quick fixes
dart analyze .                             # Only shows issues needing manual attention

Testing

dart test --reporter=failures-only packages/<pkg>/test/unit/   # Only prints failures

IMPORTANT: Never run integration tests (which hit live APIs) unless explicitly requested by the user — they are expensive. Only run unit tests by default by targeting test/unit/ directories (e.g., dart test --reporter=failures-only packages/<pkg>/test/unit/).

Test placement rules:

test/integration/ — Tests that hit live external APIs (require API keys, network access). Must be tagged with @Tags(['integration']) and include a library; directive so CI can exclude them.
test/unit/ — All other tests, including tests with local HttpServer, MockClient, or any self-contained test that does not call external services. These run in CI by default.

Read the full file on GitHub · 128 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.

9d ago First seen · 128 lines · 1,178 tokens per session scan A 0cd294d8fc94

Subscribe to this mod's changes

ai_clients_dart AGENTS.md is an instructions file published in the GitHub repository davidmigloz/ai_clients_dart (24 stars, last pushed today), licensed MIT. It adds 1,178 tokens to every session, about $0.0059 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.

Languages

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

ai_clients_dart: Instructions file for Codex