From modelharness
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/modelharness:memory-disciplineThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fable 5 performs notably better when it can write learnings somewhere for future
Fable 5 performs notably better when it can write learnings somewhere for future reference. Give Opus the same surface and rules.
MEMORY.md (index) if present, then any
lessons/*.md whose one-line summary looks relevant.lessons/, kebab-case name, one-line summary on the first line.MEMORY.md.<!-- 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.
npx claudepluginhub vitaliikapliuk/modelharness --plugin modelharnessRecords reusable lessons from resolved bug fixes, architectural changes, interface updates, or recurring pitfalls into project memory docs, anchored to git commits.
Captures durable project learnings from conversations or git history and routes them to memory, decision records, rules, or skills. Scores each candidate and confirms before writing.
Distills session lessons into project memory files (facts, patterns, failures) with compiled truth and evidence log layers. Used as final step of a goal loop or on user correction.