You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Reviews pull requests for the shortcuts AI coding agents take to look done without being done: relaxed tests, swallowed errors, fake renames, 11 checks in all. Flags them for a human by default, or blocks the merge if you turn that on. Can also turn a goal into a checklist and only accept a patch once every check passes.
Merge gates and safety checks for AI coding agents. Works with Claude Code, Cursor, Windsurf, Codex via MCP. Detect scope violations, missing tests, and risks before merge.
Deterministic verify-gate for AI code changes — apply only if green, else refuse (WRONG-APPLY=0). The safety layer between any coding agent and your repo.
Security gates for AI-generated code changes. Open Agent Security scans PR diffs, detects security-sensitive changes, requires verification evidence, and blocks risky merges before they ship.
Author-aware merge gate: holds autonomous-agent PRs to a provably-done bar (spec · build · tests · checks) before they touch main. GitHub gates on branches; mergegate gates on who opened the PR.
One ship/no-ship verdict from aiglare, bouncer, tieline & repoctx — the unified merge gate for the nugehs toolchain. CLI, CI gate, MCP server, and a VS Code/Cursor extension.
Self-built branch protection and decision routing for solo developers using multiple AI coding agents. Vendor-neutral, GitHub Free-tier compatible, plugin-extensible.
Human ownership and merge gate for AI coding-agent diffs. Generates grounded MCQs before Claude Code, Codex, Gemini CLI, or OpenCode can push or open a PR.