Skip to content
Development
Skill

/memory-discipline

Use when recording lessons learned in a project, or when a project contains lessons/ or MEMORY.md — file-based memory format and read/write rules that measurably improve long-horizon performance.

From plugin
modelharness
363 skills1 agent3 commands1 hook
Install
$ npx -y skills add vitaliikapliuk/modelharness --skill memory-discipline --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/memory-discipline

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use when recording lessons learned in a project, or when a project contains lessons/ or MEMORY.md — file-based memory format and read/write rules that measurably improve long-horizon performance.

SKILL.md

memory-discipline.SKILL.md
name: memory-discipline
description: Use when recording lessons learned in a project, or when a project contains lessons/ or MEMORY.md — file-based memory format and read/write rules that measurably improve long-horizon performance.

Memory Discipline

Fable 5 performs notably better when it can write learnings somewhere for future reference. Give Opus the same surface and rules.

Read rules

  • At the start of non-trivial work, read `MEMORY.md` (index) if present, then any

`lessons/*.md` whose one-line summary looks relevant.

  • Memories reflect what was true when written — verify a referenced file/flag still

exists before relying on it.

Write rules

  • One lesson per file in `lessons/`, kebab-case name, one-line summary on the first line.
  • Record corrections from the user and confirmed working approaches alike — include WHY

it mattered, not just what happened.

  • Don't save what the repo already records (code structure, git history, README facts).
  • Update an existing lesson rather than creating a near-duplicate; delete lessons that

turn out to be wrong.

  • After writing, add/refresh a one-line pointer in `MEMORY.md`.

Format

<!-- lessons/use-fake-clock-in-timer-tests.md --> Timer tests must inject a fake clock — real sleeps made CI flaky.

Context: PR #42 reverted twice. `time.monotonic` is patched via the `clock` parameter; never call `time.sleep` in tests.

Read more
Ships withmodelharness

Make every model cheaper or better. Measured on four Claude models — none got worse. What it actually is: a zero-config Claude Code plugin.

Get the whole plugin
Stats
36
Stars
1
Forks
Maintained
Maintenance
Python
Language
MIT
License
3mo ago
Last commit
3mo ago
Created

Repo: vitaliikapliuk/modelharness

Other skills on modelharness.