bearing-taskcorelisted

# Task-core — a compaction save-state that kills drift When a long task runs, Claude Code **compacts**: it summarizes the conversation and drops the transcript. The generic summary keeps the gist but loses load-bearing detail — a constraint the user gave, a decision's *why*, the exact file:line you were mid-edit on, a dead-end you already ruled out. After compaction the agent **drifts**: re-litigates settled calls, repeats failed approaches, forgets requirements. The fix: **you** decide what survives. Keep a **task-core** — a dense, machine-facing save-state of the CURRENT TASK — and read it back on recovery. It's the one artifact guaranteed to survive with full fidelity. **File:** `.bearing/task-cores/<chat-id>.md` — **one per CHAT**, not one per repo. The SessionStart brief names your exact path; use that one. Gitignored; survives compaction *and* new sessions — a task can span both; overwrite it when the task changes. > Several agent sessions run in the same repository routinely (a second editor window is enough). A single shared file meant they overwrote each other, and on recovery a session would reconstruct from **another chat's task** with full confidence — the exact drift a task-core exists to prevent. If the brief gives you no path, fall back to `.bearing/task-cores/shared.md`. ## When to write / refresh it - **Unsaved-work nudge** — a PostToolUse hook counts EDITS since the core was last written and prompts after `taskCoreEveryEdits` of them (25 by default; 0