goal
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon…
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
> /plugin marketplace add vitaliikapliuk/modelharness > /plugin install modelharness@modelharness
How it fires
How this command gets triggered: by you, by Claude, or both.
/retroContext preview
What this command does when you run it.
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
description: Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
Run a short retrospective of this session and persist what is worth remembering.
1. Load the `memory-discipline` skill and follow its write rules. 2. Identify candidate lessons: user corrections, approaches that worked after failed attempts, non-obvious project facts discovered the hard way. Exclude anything the repo already records. 3. For each lesson: create/update a file in `lessons/` (one lesson per file, one-line summary first), then refresh `MEMORY.md` index lines. 4. Show the user a one-line-per-lesson summary of what was saved.
Make every model cheaper or better. Measured on four Claude models — none got worse. What it actually is: a zero-config Claude Code plugin.
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon…
Spawn a fresh-context verifier subagent to check completed work against its specification before trusting it.