Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, searchable session history.
Agent Claude Code
Deep implementation work delegated by the lead — writing kit code, writing tests (five-exit-doors discipline), debugging failures, and the implementer self-review pass on a diff. Use for any coding work bigger than a trivial edit. Runs on Opus.
Agent Claude Code
Mechanical, low-judgment work delegated by the lead — boilerplate, scaffolding, multi-file sweeps and renames, doc formatting, test fixtures, applying an exactly-specified pattern across many files. NOT for tests, logic, or anything requiring design judgment. Runs on Sonnet.
Agent Claude Code
The independent review pass on a diff or PR — ONE holistic pass over the full change (code + tests + docs together), findings ranked Blocking/Important/Minor. Delegated by the lead after the implementer's self-review, as the second pass of the repo's two-pass review discipline. Runs on Opus.