MCP server for AI coding agents - gives Claude Code, OpenCode, Cursor, and Codex CLI structural understanding of your codebase: symbol graph, blast radius, semantic search, conventions.
Agent Claude Code
Adversarial Loop 3 evaluator for the vertical bench. Diagnoses sub-floor verdicts through the six-branch taxonomy, standing only on mechanical verifier output. WIN confirmation lives in bench-win-confirm.
Agent Claude Code
Reads any bench run (validation or paid, win or loss) and returns the material for a better scenario - where the baseline struggled and what Sense reached that it did not. Never issues a verdict; never diagnoses a loss (that is bench-evaluator).
Agent Claude Code
WIN-confirmation vertex for the vertical bench. Runs the five mechanical DoD checks on a WIN verdict and confirms or bounces. Never diagnoses a sub-floor verdict; never fault-finds a clean win.
Agent Claude Code
Cheap-tier agent for mechanical work with script-checkable output - text cleanups (em-dash sweeps), pack/doc line updates, file renames, and full-read extraction that returns verbatim quotes with file:line cites. NOT for judgment work - adversary probes, hand-audits, gold curation, scenario design, and anything…