What problem does it solve? Context degradation in long AI sessions is silent and gradual: models stop attending to early instructions, and compaction summaries quietly drop standing instructions, with no visible error. This Skill installs a trivially checkable per-turn signal (a canary) so the moment context rot, drift, or compaction occurs, it becomes visible instead of corrupting work downstream. ## Core Features & Use Cases - Canary Contract Installation: Establishes a byte-stable first line on every response containing the user's name, a turn counter, and an honest self-check status (ctx ok / aging / thin). - Trip Detection & Calibration: Distinguishes a single missed canary (warning) from a confirmed trip (two consecutive misses, counter discontinuity, or agent self-declaration) to avoid false alarms. - Recovery Protocol: On a confirmed trip, checkpoints durable state to a file, re-anchors against project instructions, recommends a fresh session, and re-installs the canary with a new generation counter. - Use Case: At the start of a long refactoring session, ask the agent to install a context canary; if the name prefix or turn counter disappears after an auto-compaction event, you know immediately that earlier constraints may have been lost and can trigger the checkpoint-and-reset protocol. ## Quick Start Ask the agent to install a context canary for this session so every reply starts with your name and a turn counter.
