retro
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon quality.
> /plugin marketplace add vitaliikapliuk/modelharness > /plugin install modelharness@modelharness
How it fires
How this command gets triggered: by you, by Claude, or both.
/goalContext preview
What this command does when you run it.
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon quality.
description: Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon quality.
The user wants to start a substantial task. Do NOT start working yet.
1. Read their request: $ARGUMENTS (if empty, ask what they want to build). 2. Interview briefly — one question at a time, only for genuinely missing pieces:
output, observable behavior)? 3. Restate the complete specification in one block and get a quick confirmation. 4. Execute the full task against that spec autonomously: follow the modelharness core (grounded progress, self-verification cadence, fresh-context verification before completion claims). Do not stop to ask about minor decisions — note them instead.
Make every model cheaper or better. Measured on four Claude models — none got worse. What it actually is: a zero-config Claude Code plugin.
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
Spawn a fresh-context verifier subagent to check completed work against its specification before trusting it.