Automatically and incrementally keeps AGENTS.md up to date from transcript changes.
The plugin combines:
- A
stophook that decides when to trigger learning. - A
continual-learningskill that orchestrates the learning flow. - An
agents-memory-updatersubagent that mines new or changed transcripts and updatesAGENTS.md.
It is designed to avoid noisy rewrites by:
- Reading existing
AGENTS.mdfirst and updating matching bullets in place. - Processing only new or changed transcript files.
- Writing plain bullet points only (no evidence/confidence metadata).
/add-plugin continual-learningOn eligible stop events, the hook may emit a followup_message that asks the agent to run the continual-learning skill.
The skill is marked disable-model-invocation: true, so it will not be auto-selected during normal model invocation. When it does run, it delegates the full memory update flow to agents-memory-updater.
The hook keeps local runtime state in:
.cursor/hooks/state/continual-learning.json(cadence state)
The updater uses an incremental transcript index at:
.cursor/hooks/state/continual-learning-index.json
Default cadence:
- minimum 10 completed turns
- minimum 120 minutes since the last run
- transcript mtime must advance since the previous run
Trial mode defaults (enabled in this plugin hook config):
- minimum 3 completed turns
- minimum 15 minutes
- automatically expires after 24 hours, then falls back to default cadence
CONTINUAL_LEARNING_MIN_TURNS(or legacyCONTINUOUS_LEARNING_MIN_TURNS)CONTINUAL_LEARNING_MIN_MINUTES(or legacyCONTINUOUS_LEARNING_MIN_MINUTES)CONTINUAL_LEARNING_TRIAL_MODE(or legacyCONTINUOUS_LEARNING_TRIAL_MODE)CONTINUAL_LEARNING_TRIAL_MIN_TURNS(or legacyCONTINUOUS_LEARNING_TRIAL_MIN_TURNS)CONTINUAL_LEARNING_TRIAL_MIN_MINUTES(or legacyCONTINUOUS_LEARNING_TRIAL_MIN_MINUTES)CONTINUAL_LEARNING_TRIAL_DURATION_MINUTES(or legacyCONTINUOUS_LEARNING_TRIAL_DURATION_MINUTES)
The memory updater writes only:
## Learned User Preferences## Learned Workspace Facts
Each item is a plain bullet point.
MIT