Menu
Run the memhub retrieval eval harness from OpenCode; use to check Recall@K quality.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Read-only health check of the memhub project in this repo — schema version, render freshness, write-log activity
Bootstrap memhub in this repo — initialize the SQLite store, seed starter state and architecture narratives, render PROJECT.md and PROJECT_LEDGER.md
Initialize memhub for a repo in OpenCode; use when the user asks to bootstrap project memory.
Summarize this memhub session, route updates into the database, then re-render PROJECT.md and PROJECT_LEDGER.md
Rebuild + install memhub and bring every memhub instance on this machine (each known repo DB + the machine-global store) to head schema, resync installed agent skill wrappers, with a one-time fix for the ~/.local/bin PATH shadow. Run from the memhub source repo.
Wrap up an OpenCode memhub session; run the binary-rendered policy, draft updates, get per-item approval, write, and render.
| name | eval-recall |
| description | Run the memhub retrieval eval harness from OpenCode; use to check Recall@K quality. |
| compatibility | opencode |
Run the read-only retrieval evaluation harness.
Workflow:
memhub eval retrieval from the memhub source repo.memhub eval retrieval --no-rerank if the user asks for reranker A/B data..memhub/project.sqlite (a calibration signal, not the enforced baseline). The deterministic reference is cargo test retrieval_golden_hermetic (issue #44) — see docs/reference/operations.md.