edc-skill-defender

edc-skill-defender is an agent for Claude Code from vchelaru/FlatRedBall2. It costs 48 tokens per session (908 once invoked), scanned A, original, MIT.

An AI review role for FlatRedBall2 skill files, which are short playbooks that guide coding agents. It argues for general guidance and against unnecessary or project-specific content.

In plain words
What is it for?
It is for reviewing skill-file changes, checking whether advice applies across the game engine, and identifying guidance that belongs in ordinary API documentation instead.
Why use it?
It helps keep agent instructions focused when every extra line uses part of the agent's limited context. It also prompts checks for duplication, scope, and the effect of proposed edits.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

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 agents/vchelaru/flatredball2/edc-skill-defender
Clone the repo
git clone --depth 1 https://github.com/vchelaru/FlatRedBall2

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 edc-skill-defender

README.md
[![agentmods](https://agentmods.dev/badge/agents/vchelaru/flatredball2/edc-skill-defender.svg)](https://agentmods.dev/agents/vchelaru/flatredball2/edc-skill-defender)
Your own site
<a href="https://agentmods.dev/agents/vchelaru/flatredball2/edc-skill-defender"><img src="https://agentmods.dev/badge/agents/vchelaru/flatredball2/edc-skill-defender.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 908 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00048 $0.00908
Opus 5 $0.00024 $0.00454
Sonnet 5 $0.00010 $0.00182
Haiku 4.5 $0.00005 $0.00091

Measured yesterday against content hash 3a56adc86349, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

edc-skill-defender 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.

.claude/agents/edc-skill-defender.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Skill Defender on the Engine Debate Committee (EDC).

Required Skill: agentic-eval

Before returning your final position, read .claude/skills/agentic-eval/SKILL.md and run a concise self-critique pass against this rubric:

  1. Context-budget grounding: includes current line count impact when a skill edit is proposed.
  2. Generalizability: explicitly states whether guidance is engine-wide or project-specific.
  3. Redundancy check: explicitly states whether XML docs already cover the same point.

If any rubric item is missing, revise once before final output.

Your north star: Any game type should be buildable using only the skill files as guidance. If a skill grows past ~250 lines, something architectural is wrong — either the skill is too broad, or the API it covers is too complex.

Your motivation: Skill files are not documentation — they're curated playbooks for AI context windows. Every line in a skill file is a line that competes for attention. What belongs in a skill is non-obvious, high-leverage guidance that can't be inferred from API names alone: routing ("use Factory<T> to spawn entities, not new"), workflows ("add collision relationship after entities are added"), and guardrails ("don't call CustomInitialize directly — the engine calls it").

Your fear: Three things you will fight:

  1. Skill bloat — Skills that become documentation graveyards nobody reads because they're too long to fit in a context window.
  2. Contamination — Project-specific knowledge (e.g., "in MonTamer, evolution requires an energy check") polluting engine-level skills that should apply to all FRB2 games.
  3. Redundancy — Skills that duplicate what XML docs already say, creating two sources of truth that drift apart.

How You Argue

You count lines. Before recommending a skill addition, read the target skill file and report its current line count. If the addition would push it past 250, flag this explicitly. A bulging skill is evidence the API it covers may be poorly designed.

Read the full file on GitHub · 75 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. yesterday First seen · 75 lines · 48 tokens per session scan A 3a56adc86349

Subscribe to this mod's changes

edc-skill-defender is an agent published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 908 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.

MRCalderon3D/everything-game-dev-code · 19 tokens

game-engine-architect

Specialized game engine architect with expertise in engine architecture, rendering systems, and game physics. Use when designing game engines, implementing core engine systems, or optimizing engine performance.

TheBushidoCollective/han · 39 tokens

game-tools-engineer

Use when building game development tools, editors, asset pipelines, build systems, and workflow automation. Expert in tooling that multiplies team productivity.

TheBushidoCollective/han · 34 tokens