flutter-ai-rules AGENTS.md

Concise project rules for Flutter AI Rules, a set of instructions for coding agents working on Flutter apps. They cover file organisation, commit titles, skill descriptions, browser deployment, and a completion sound.

In plain words
What is it for?
Use them when editing Flutter projects, creating skills, deploying to Chrome, changing assets or dependencies, or preparing commit titles.
Why use it?
They keep changes small and consistent across app work, while reminding the agent about project-specific actions after tasks and deployments.

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/evanca/flutter-ai-rules/agents-md
Clone the repo
git clone --depth 1 https://github.com/evanca/flutter-ai-rules

Made for: Codex, OpenCode.

Per session 156 This file is loaded in full into every session.
When invoked 156 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 $0.00156 $0.00156
Opus 5 $0.00078 $0.00078
Sonnet 5 $0.00031 $0.00031
Haiku 4.5 $0.00016 $0.00016

Measured 3d ago against content hash 4e9699364171, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flutter-ai-rules 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 3d 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 · 9 lines

What it actually says

Global Agent Rules

  1. Be concise. The owner works on several apps in parallel and has limited time to read your outputs; don't use a full paragraph when a single short sentence will do.
  2. Keep files small and modular; split large files into reusable parts.
  3. After each task, run afplay /System/Library/Sounds/Glass.aiff.
  4. After each step, suggest a short commit title: Implement dashboard for features; Fix: Problem for fixes. Use no other prefixes.
  5. After deploying Flutter to Chrome, press r; restart it if pubspec.yaml or assets changed.
  6. Write every skill’s YAML description on one line starting with Use when; include only trigger conditions.
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. 3d ago First seen · 9 lines · 156 tokens per session scan A 4e9699364171

Subscribe to this mod's changes

flutter-ai-rules AGENTS.md is an instructions file published in the GitHub repository evanca/flutter-ai-rules (622 stars, last pushed 5d ago), licensed MIT. It adds 156 tokens to every session, about $0.0008 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.