recall

Recall

Before you start or resume work, you rebuild the user's recent working context and hand back a tight capsule of where things stand now and what to do next. Use for "recall my work on X", "catch me up", "what have I been working on", or "where did I leave off".

Keep it tight and on-topic. Read only what the in-scope threads need, then stop. The heavy reading fans out to parallel subagents. The main thread keeps only their findings and the final brief.

Your context lives in two records. Your own chat history holds what you did and decided. The shared record holds everything that happened around the same code under other names: the symptoms users keep reporting, the fixes that shipped and got reverted, the errors still firing in prod. That second record is what the why skill searches, across source control, the issue tracker, chat and issue channels, long-form docs, and error tracking. A feature with a long bug tail keeps most of its story there, so don't reconstruct it from your transcripts alone.

Use the active host's thread history, transcript API, or current-session context. Do not guess private filesystem paths or scan unrelated projects. If the host exposes no prior history, reconstruct from the repository and the context the user supplied.

1. Classify, then route. One specific prior chat to resume is the session-pickup playbook, not this. A human-readable summary of your work is a different task. Recall loads working context across recent chats before you act. If the user already gave you a full state capsule with paths, branch, and change, use it and skip the mining.
2. Lock the scope before searching. Pin the window ("recent" is a real range, default the last 7 days), the topic if named, and the workspace (default the active one; never read another project's transcripts without being asked). State the scope back. Never quietly turn "all" into "recent N".
3. Search the available chat history. When subagents are available and permitted, give each one a disjoint time slice. Otherwise search inline. Order candidates by real modification time, search the topic first, read only matching regions, and skip the current chat plus obvious subagent, eval, and test noise. Return one block per chat with the topic, user goal, decisions, open threads, corrections, and artifacts. Cite the host's stable task or chat identifier when one exists.
4. Sweep the shared record whenever the topic names a feature, file, subsystem, area, or bug. This is the default, not a judgment call, and "my work on X" does not exempt it. A named target carries history you never see in your own transcripts, and that history is the point of the sweep. Hand it to the why skill's source investigators, but steer their question from "why was this built this way" to "what's the current state, what's been tried and didn't hold, and what are users still reporting". Reuse its per-source playbooks so you don't reinvent each query vocabulary, run the investigators in parallel with the chat-history mining, and inherit its posture: one investigator per source, null results are findings, skip an unavailable MCP and say so. Fold what comes back into the brief. Skip this step only for pure activity recall with no named target ("what did I do this week"), where your own history and live state are the entire answer.
5. Verify against live state. A transcript or a stale ticket is history, not current truth, so take the PRs, branches, and tickets that the mining and the sweep surfaced and check them with git and gh. When the answer hinges on what an agent actually did (the tools it ran, files it read, errors it hit), read the full transcript, not just a trimmed local copy.
6. Write the brief to the contract below. Group by thread. Stay on the named topic.