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/vchelaru/flatredball2/claude-mdgit clone --depth 1 https://github.com/vchelaru/FlatRedBall2Wrote 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/vchelaru/flatredball2/claude-md)<a href="https://agentmods.dev/instructions/vchelaru/flatredball2/claude-md"><img src="https://agentmods.dev/badge/instructions/vchelaru/flatredball2/claude-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 5.1 | $0.03698 | $0.03698 |
| Opus 5 | $0.01849 | $0.01849 |
| Sonnet 5 | $0.00740 | $0.00740 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade A, and why
FlatRedBall2 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 yesterday.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@design/TODOS.md
Repository Guidelines
What Is This?
FlatRedBall2 is a 2D game engine/framework written in C# on .NET, built on top of MonoGame. It integrates Gum (UI) and Tiled (level editing) as dependencies.
Prerelease Status — Breaking Changes Are Free
FlatRedBall2 is in active prerelease development. There are no shipping consumers, no public API surface to preserve, and no backwards-compatibility obligations. Anything in the engine — type names, method signatures, namespaces, defaults, semantics — can be changed at any time if a better design exists.
When proposing or evaluating a change:
- Do not raise "this will break existing code" as a concern. It is not a concern. Existing call sites in samples and tests are part of this codebase and will be updated alongside the change.
- Do not add deprecation shims,
[Obsolete]attributes, alias members, or "kept for compatibility" wrappers. Just change the thing. - Do propose the cleanest API; if a rename or restructuring makes the engine clearer, it is on the table.
The only relevant question is "is this the right design?" — never "will this break someone?"
Key Files
- Main project:
src/FlatRedBall2.csproj(MonoGame.Framework.DesktopGL, version pinned in the rootDirectory.Packages.props) - Code style:
.claude/code-style.md - Deferred items:
design/TODOS.md - Multi-phase plans:
plan/plan.md(index) — see below - Test project:
tests/FlatRedBall2.Tests/FlatRedBall2.Tests.csproj
Multi-Phase Plans (plan/)
Create a plan only when the user explicitly asks for one. Start work on <issue> means implement, test, push, and open a PR; do not stop at a plan or plan-only commit.
plan/plan.mdis the table of contents. One row per phase, linking to that phase's document, with a status. It never holds phase content itself. Read it first when picking up large work.- Phase documents live in
plan/<issue#>-<initiative-slug>/phase-NN-<slug>.md. Each is self-contained: the issue restated, the high-level proposed resolution, features/stories, and every step as a checkbox. A reader should not need the GitHub issue open to work the phase. - Write the next phase doc when the previous phase is stable, not all up front — plans written before any code exists are wrong by the time they are read.
- Check boxes off as work lands, and update the status row in
plan/plan.md. Add discovered work as new checkboxes rather than silently widening an existing one.
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.
- yesterday First seen · 200 lines · 3,698 tokens per session scan A 196b7937e8d1
FlatRedBall2 CLAUDE.md is an instructions file published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed today), licensed MIT. It adds 3,698 tokens to every session, about $0.0185 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 2026-09-04.
Other instructions, from other repositories
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).