A staged spec → plan → coding → review workflow for shipping AI-assisted code. Works with Claude Code, Codex, Cursor & Antigravity.
This repository also configures its own agents. See what specship tells them →
Agent Claude Code
Read-only search worker for the specship pipeline. Use to delegate one wide fan-out sweep when a stage needs an answer that means reading many files — it returns verified conclusions only, so the caller's context stays clean. A stage invokes it, never a user directly; it never writes or changes code.
Agent Claude Code
External-fact search worker for the specship research stage. Use to run one query angle of a larger question and return verified, cited conclusions. One invocation per angle — it gathers and checks its own sources, and it neither picks the angles nor writes the report.
Agent Claude Code
Independent code reviewer for the specship review stage — one member of the opt-in review panel. Use to get fresh, context-free eyes on a working diff, optionally through a named lens (correctness, security, performance, contract-consistency). Reports findings only; it does not fix code, decide the verdict, or touch…