delegation-triggers
Use when deciding whether to spawn subagents — explicit rules for when delegation pays off and when direct work is faster. Opus 4.8 under-delegates by default;…
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.
$ npx -y skills add vitaliikapliuk/modelharness --skill memory-discipline --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/memory-disciplineContext 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.
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.
Fable 5 performs notably better when it can write learnings somewhere for future reference. Give Opus the same surface and rules.
`lessons/*.md` whose one-line summary looks relevant.
exists before relying on it.
it mattered, not just what happened.
turn out to be wrong.
<!-- 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.
Make every model cheaper or better. Measured on four Claude models — none got worse. What it actually is: a zero-config Claude Code plugin.
Use when deciding whether to spawn subagents — explicit rules for when delegation pays off and when direct work is faster. Opus 4.8 under-delegates by default;…
Use when a task spans more than a few steps or files — establishes a checkable definition of done, a verification cadence, and fresh-context verifier subagents…