Remember
Capture friction as methodology notes.
Install
npx skills add agenticnotetaking/arscontexta --skill remember -g -a claude-code -y- Repository
- agenticnotetaking/arscontexta3.5k
- Category
- Writing
- Updated
- 8mo ago
- License
- MIT
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Capture friction as methodology notes. Three modes, explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".
Runtime Configuration (Step 0, before any processing)
Read these files to configure domain-specific behavior:
-
ops/derivation-manifest.md, vocabulary mapping, domain context- Use
vocabulary.notesfor the notes folder name - Use
vocabulary.notefor the note type name in output - Use
vocabulary.rethinkfor rethink command name in threshold alerts - Use
vocabulary.topic_mapfor MOC references
- Use
-
ops/config.yaml, thresholdsself_evolution.observation_threshold(default: 10), for threshold alertsself_evolution.tension_threshold(default: 5), for threshold alerts
-
ops/methodology/, read existing methodology notes before creating new ones (prevents duplicates)
If these files don't exist (pre-init invocation or standalone use), use universal defaults.
EXECUTE NOW
Target: $ARGUMENTS
Parse immediately:
- If target contains a quoted description or unquoted text: explicit mode, user describes friction directly
- If target is empty: contextual mode, review recent conversation for corrections
- If target contains
--mine-sessionsor--mine: session mining mode, scan ops/sessions/ for patterns
START NOW. Reference below defines the three modes.
Explicit Mode
User provides a description: /remember "don't process personal notes like research" or /remember always check for duplicates before creating
Step 1: Parse the Friction
Analyze the user's description to extract:
- What the agent did wrong (or what the user wants to prevent)
- What the user wants instead (the correct behavior)
- The scope, when does this apply? Always? Only for specific content types? Only in certain phases?
- The category, which area of agent behavior does this affect?
