Edc Reality Tester — Data & AI agent for Claude Code
EDC sub-agent.
How to install Edc Reality Tester
Installs to ~/.claude/agents/vchelaru-flatredball2-edc-reality-tester.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vchelaru/FlatRedBall2/HEAD/.claude/agents/edc-reality-tester.md -o ~/.claude/agents/vchelaru-flatredball2-edc-reality-tester.md Restart Claude Code, or start a new session, for it to be picked up.
What Edc Reality Tester does
name: edc-reality-tester description: EDC sub-agent. Tests whether proposed documentation or API changes would actually improve AI assistant behavior. Frequently argues that the real friction is the API design, not missing docs. tools: Read, Grep, Glob
You are the **AI Reality Tester** on the Engine Debate Committee (EDC).
Required Skill: agentic-eval
Before finalizing your response, read `.claude/skills/agentic-eval/SKILL.md` and apply a one-pass evaluator-optimizer check:
- Ens
Alternatives in Data & AI
- Docs Drift Reviewer — Checks whether clickhouse-go documentation matches changes to its ClickHouse API, database/sql API, transports 3.3k ★
- Authz Reviewer — PYA specialist spawned by the /pya orchestrator 240 ★
- Review Code Robustness — A code review agent that checks analysis scripts for fragile patterns, missing error handling at data boundari 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Edc Skill Defender
EDC sub-agent. Defends the FlatRedBall2 skill files as curated AI playbooks. Argues for lean, generalizable sk
Design UX Researcher
Expert user experience researcher specializing in user behavior analysis, usability testing, and data-driven d
Engine Design Review Feasibility
Before a change you've asked for gets built, checks whether the plan can actually be built, shipped, and run —
Agentic Search Optimizer
Expert in WebMCP readiness and agentic task completion — audits whether AI agents can actually accomplish task
SEO AI Access Checker
Checks whether AI and search crawlers can actually reach a URL, and whether its content is in the served HTML
Game AI Programmer
In-game AI programmer sub-agent. Produces behavior trees / GOAP / Utility / HTN / EQS / NavMesh / perception s
Related Skills
P Reality Check
Assess whether the project actually has the intended thing
Skill Trigger Lab
Lint, score and live-test whether an agent SKILL.md actually gets triggered. Deterministic offline frontmatter
Find Wasted Code
Run the find-wasted-code audit — the code-per-friction sibling of /token-waste-audit and /find-wasted-effort.