flutter-flame-harness: Instructions file for Claude Code

CLAUDE.md

flutter-flame-harness CLAUDE.md is an instructions file for Claude Code from tjdrhs90/flutter-flame-harness. It costs 864 tokens per session, scanned A, original, MIT.

A contributor guide for developing the Flutter Flame Harness plugin, a tool for creating Flame game projects in Flutter.

In plain words
What is it for?
Use it when editing the plugin's skills, documentation, scripts, or templates, rather than when building an individual game.
Why use it?
It gives maintainers a consistent process for planning, building, reviewing, and testing changes to the plugin itself. It also sets rules such as stating assumptions and keeping changes focused.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents.

This is tjdrhs90/flutter-flame-harness's own configuration. It tells Claude Code how to work on flutter-flame-harness 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 flutter-flame-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tjdrhs90/flutter-flame-harness. 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/tjdrhs90/flutter-flame-harness/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tjdrhs90/flutter-flame-harness

Made for: Claude Code.

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 flutter-flame-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tjdrhs90/flutter-flame-harness/claude-md.svg)](https://agentmods.dev/instructions/tjdrhs90/flutter-flame-harness/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tjdrhs90/flutter-flame-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/tjdrhs90/flutter-flame-harness/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 864 This file is loaded in full into every session.
When invoked 864 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 $0.00864 $0.00864
Opus 5 $0.00432 $0.00432
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00086 $0.00086

Measured 7d ago against content hash 7a3f9df8b56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

flutter-flame-harness CLAUDE.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 7d 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

flutter-flame-harness — Development Guide

한국어 소개는 README.ko.md 를 참고하세요.

This guide is for developing/contributing to this plugin repo itself — the skills/, docs/, scripts/, and templates/ that make up the plugin, not the games it generates.

Philosophy: don't vibe-code — delegate the procedure to a disciplined workflow. Question → plan → build → review, with humans owning direction and final QA. This workflow is tool-agnostic and depends on no external plugins; follow it by hand, or with whatever tooling you happen to have.

This harness is itself a game-specific instance of this same philosophy: hard gates / the contract = guardrails, research·plan = clarify·plan, the generator↔evaluator loop = build-until- verified + independent review. So we develop the plugin the same way it builds games.


Always-on guardrails

Apply these on every edit, review, and refactor — by default:

  1. Think before coding — state assumptions; if multiple readings exist, surface them and ask. Don't silently pick.
  2. Simplicity first — the minimum that solves the task. No speculative abstraction, configurability, or features that weren't requested.
  3. Surgical changes — touch only the lines the request requires. Match existing style. Don't refactor what isn't broken; if you spot unrelated dead code, mention it rather than delete it.
  4. Goal-driven — turn the task into a verifiable success check, then loop until it passes ("make this command pass" beats "make it work").

Development flow

  1. Clarify — before writing code, agree on intent, constraints, and success criteria, and get the design approved. Don't start on ambiguous requirements.
  2. Plan — write a task-by-task implementation plan under docs/superpowers/plans/. Decide the test/verification strategy up front.
  3. Build — implement task by task. Prefer isolated-context sub-agents (one per task) with a two-stage review (spec compliance → code quality); or run in batches with human checkpoints. Isolation keeps each unit's context clean and the main thread focused on coordination.
  4. Review — a fresh, independent pass over the diff (bugs / duplication / efficiency) before merge. It's a first filter from a clean context, not a replacement for human review.
  5. Human QA — design direction and business fit are the human's call. Treat review findings as input, not orders; reject false positives.

Read the full file on GitHub · 71 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. 7d ago First seen · 71 lines · 864 tokens per session scan A 7a3f9df8b56c

Subscribe to this mod's changes

flutter-flame-harness CLAUDE.md is an instructions file published in the GitHub repository tjdrhs90/flutter-flame-harness (59 stars, last pushed 5d ago), licensed MIT. It adds 864 tokens to every session, about $0.0043 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

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 · 5,182 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

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

langchain AGENTS.md

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 · 4,469 tokens

spec-kit AGENTS.md

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 · 7,104 tokens