Risk-adaptive development pipeline with adversarial consensus code review
Agent
Parses a user feature request into a structured contract.json. Scans codebase for scope signals and risk assessment. Read-only -- never writes code files, only generates contract.json.
Agent
Implements code changes according to a contract.json specification. The ONLY agent in Signum that writes code. Includes a repair loop: generate -> check -> fix -> check (max 3 attempts).
Agent
Synthesizes project.intent.md and project.glossary.json from deterministic scan signals. Uses ranked source hierarchy and explicit-only Non-Goals extraction. Emits per-section evidence comments and confidence annotations. Read-only — never writes files directly (presents draft for user confirmation).
Agent
Semantic code reviewer using Claude Opus. Part of the multi-model audit panel. Analyzes diff against contract for bugs, security issues, and logic errors. Read-only -- never modifies code.
Agent
Combines multi-model review results into a consensus verdict. Reads review outputs from Claude, Codex, and Gemini, plus mechanic report. Applies deterministic synthesis rules to produce final audit decision. Read-only -- never modifies code.