mcp_dart AGENTS.md

Repository instructions for mcp_dart, a Dart software development kit and command-line package for MCP, the protocol that lets AI assistants communicate with tools and data sources. They describe its code layout, compatibility priorities, engineering principles, tests, and release process.

In plain words
What is it for?
Use them when editing the Dart SDK, CLI, tests, protocol schemas, release automation, or documentation, and when preparing a release.
Why use it?
They give coding agents clear rules for preserving protocol correctness and compatibility while changing the SDK or CLI.

Instructions file for CodexOpenCode

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/leehack/mcp_dart/agents-md
Clone the repo
git clone --depth 1 https://github.com/leehack/mcp_dart

Made for: Codex, OpenCode.

Per session 1,196 This file is loaded in full into every session.
When invoked 1,196 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 $0.01196 $0.01196
Opus 5 $0.00598 $0.00598
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured 2d ago against content hash 04c30ef6e5e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp_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 2d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp_dart Agent Guidelines

Use this file for durable, repository-specific rules. Keep detailed procedures in focused docs and runbooks.

Priorities

  1. MCP and JSON-RPC specification correctness.
  2. Backward compatibility and cross-SDK interoperability.
  3. Simple, maintainable code.
  4. Evidence-backed delivery: tests, examples, CI, and clean review threads.

Repository shape

  • SDK: lib/, public barrel lib/mcp_dart.dart, minimum Dart 3.4.
  • CLI: packages/mcp_dart_cli/, minimum Dart 3.12.
  • Tests: test/ and package-local test/ directories.
  • Release automation: .github/workflows/ and tool/release/.
  • Release process details: tool/release/README.md and doc/mcp-2026-07-28-release-runbook.md.

Engineering principles

  • KISS: Prefer the smallest clear design that preserves protocol behavior. Avoid speculative features, hidden normalization, and clever control flow.
  • SOLID: Keep types and modules cohesive, make dependencies and capability boundaries explicit, and extend behavior without destabilizing existing APIs.
  • DRY: Keep protocol constants, version parsing, schemas, and release rules in one source of truth. Reuse shared behavior when copies must stay identical; do not introduce an abstraction merely to remove a few obvious lines.
  • Minimize direct and transitive dependencies. Do not add a dependency or raise a package's minimum Dart version without explicit human approval. Before requesting approval, document the need, alternatives, compatibility impact, and transitive footprint.
  • Optimize measured or structurally clear hot paths. Do not trade correctness or readability for unproven micro-optimizations.
  • Preserve public API compatibility unless a breaking change is explicitly approved and documented with migration guidance.

Protocol quality bar

  • Treat the official MCP specification as authoritative. Convenience APIs must not distort wire-level JSON-RPC/MCP semantics.
  • Preserve request IDs, metadata, method names, capability flags, error codes, and transport-specific behavior unless the specification permits otherwise.
  • Distinguish advertised capabilities from runtime support and validate both.
  • Keep lower-level protocol behavior observable and testable when adding ergonomic helpers.
  • When a spec version is new or ambiguous, encode the compatibility decision in regression tests and cite the spec or rationale in focused documentation.

Read the full file on GitHub · 116 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. 2d ago First seen · 116 lines · 1,196 tokens per session scan A 04c30ef6e5e6

Subscribe to this mod's changes

mcp_dart AGENTS.md is an instructions file published in the GitHub repository leehack/mcp_dart (114 stars, last pushed 8d ago), licensed MIT. It adds 1,196 tokens to every session, about $0.0060 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.

Related

Other instructions, from other repositories

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 · 5,182 tokens

buildNext

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

next.js 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

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).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens