Your coding agent gaslights you. GODKILLER doesn't. Disk gates > vibes. claim_done only after verify.
Phase kernel for Google Antigravity. Plan. Gate. Prove on disk. Then claim done — or get blocked.
Contact: Facebook · Instagram @Kayvin.th
Antigravity skips phases. GODKILLER does not allow that.
Failure mode Kernel response --- --- No /plan plan / phase gates Multi-file rush /ultradeep one-file think → plan → edit Fake “done” verifybundle + claimdone block (server-authored evidence only) Session amnesia marathon + memory graph Weak review LLM council — Coder / Hacker / Optimizer, multi-round debate
Arena — Antigravity A/B (the real proof)
Pre-solved twins that both pass 516 prove nothing. The honest protocol:
1. Reset arms to sealed buggy 1ORIGINAL 2. You open Antigravity on 3WITHOUTMCP with MCP off → agent tries → we score 3. Reset / open 2WITHMCP with MCP on → agent tries → we score 4. Compare 11 dimensions (fail-closed on missing evidence)
Control Value --- --- Arena root GODKILLERISOLATEDARENA / GODKILLERARENAROOT Baseline 1ORIGINAL (never edit mid-run) Bare 3WITHOUTMCP GODKILLER 2WITHMCP Oracle sealed hiddenoracle/ Protocol benchmarks/ANTIGRAVITYABPROTOCOL.md
Dimension ---: --- 1 Code correctness (oracle pass %) 2 Oracle volume (≥516 collected) 3 Output integrity (full pytest body) 4 Delta from baseline (files actually changed) 5 Reconnaissance / exhaustive read artifacts 6 Phase discipline (task / plan / marathon) 7 Blast radius + edit-safe 8 Verify bundle + claimdone 9 Council (Coder / Hacker / Optimizer) 10 Security hardening signals 11 UI visual gate (critic / screenshots)
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/taurus42119-stack--godkiller-mcp.html)
Neuronto Agentic Resource Discovery (ARD) Index. Federated search across every public ARD registry, plus a verified tool index read from each MCP server's own tools/list, hybrid lexical and semantic r
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
SysikNagibator/AiPCGive the agent "this" and he gets a real PC.
iflytek/dolphin-mcp-pilotProduction-ready MCP server that lets AI agents build, schedule, run and recover Apache DolphinScheduler data pipelines - 53+ tools, beyond read-only.
ahadkhan9/workspace-mirror-skill mshanghai570/BlackBox-MCPConfigurable AI agent orchestration, delegation, memory, and project context through MCP.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.