Sub Anti Gaming Monitor — Development agent for Claude Code
Dept 4 sub. Detects weakened tests, changed criteria, fake evidence, self-approval, and protected-verification tampering.
How to install Sub Anti Gaming Monitor
Installs to ~/.claude/agents/hrk-1998-ai-agent-team-sub-anti-gaming-monitor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/hrk-1998/ai-agent-team/HEAD/agents/sub-anti-gaming-monitor.md -o ~/.claude/agents/hrk-1998-ai-agent-team-sub-anti-gaming-monitor.md Restart Claude Code, or start a new session, for it to be picked up.
What Sub Anti Gaming Monitor does
name: sub-anti-gaming-monitor description: "Dept 4 sub. Detects weakened tests, changed criteria, fake evidence, self-approval, and protected-verification tampering. Read-only." tools: [Read, Grep, Glob]
You are sub-anti-gaming-monitor under team-lead-qa. Model: same-as-lead. Isolated memory.
Input (EN from lead)
Test diffs + criteria history + evidence chain + approver identity.
Workflow
- SCAN for: deleted/weakened tests, altered acceptance to fit code, fabricated evidence,
Alternatives in Development
- Gitnexus Docs Dod Reviewer — GitNexus docs and Definition-of-Done reviewer 45.8k ★
- Monitor Setup — You are a monitoring and observability expert specializing in implementing comprehensive monitoring 31.9k ★
- Enable Monitor Mode — airmon-ng start wlan0 airodump-ng wlan0mon airodump-ng -w capture_prefix --output-format pcap,csv wlan0mon kis 213 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Resilience Anti Tamper Auditor
Audits anti-tampering and reverse-engineering resistance, including root/jailbreak detection, debugger/Frida/h
Methodology Integrity
Methodology Integrity reviewer for final phase of meerkat-comms. Detects process gaming: stubs in completed co
Sub Context Monitor
Dept 6 sub. Predicts context exhaustion and triggers safe handoff before the window fills. Read-only.
Pi Coach En
PI Wisdom-in-Action Coach v20 — monitors teammate progress with classical Chinese wisdom and MBTI cognitive st
Kotlin Convention Validator
Kotlin-only. Detects and auto-fixes convention violations in changed .kt files (git diff HEAD). Exits immediat
Impact Tracer
Read-only blast-radius mapper for Savi repos (DSP and main line; detects which). Given a changed interface, se
Related Skills
Code Quality Skill
Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampe
Trustline
Trusted baseline + auto-rollback for AI agent config files (.claude/, AGENTS.md, .mcp.json). Detects prompt-in
TDD Lock
TEST-LOCK — commit the red tests, then make them mechanically read-only while implementing to green (the stron