A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Antigravity/Gemini)
Agent
Dispatched by the doc-gen workflow to generate reference documentation for a specified target (module, package, file). Reads source directly, matches existing doc style, and emits an overview + API reference + usage examples + configuration notes.
Agent
Dispatched by self-improve, self-lint, self-perf, and refactor workflows to apply targeted code improvements (lint fixes, perf optimizations, refactors) while preserving behavior. Edits files directly and reports the diff.
Agent
Dispatched by research, deep-research, onboard, and scrape workflows to gather and synthesize information from code, web pages, or documentation. Read-only; returns structured findings, never edits files.
Agent
Dispatched by tri-review, mega-pr, and pr-ready workflows to perform an independent code review or to classify unresolved PR review comments into codefix, stylenit, question, falsepositive, or outofscope. Read-only; returns findings and classifications.
Agent
Dispatched by tri-security, audit, and pr-ready workflows to audit code for vulnerabilities across injection, auth, secrets management, dependencies, and unsafe patterns. Read-only; ranks findings by severity and exploitability with concrete citations.
Agent
Dispatched by the test-gen workflow to generate tests for a target file or module, then iterate on failing tests until they pass. Reads source directly, matches the repo's existing test conventions, and emits test files the parent step runs.