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…
@vitaliikapliukView SkillDevelopment
Skill
/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; these rules correct that.
Install
$ npx -y skills add vitaliikapliuk/modelharness --skill delegation-triggers --agent claude-codeHow 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
/delegation-triggers
Context preview
The summary Claude sees to decide when to auto-load this skill.
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; these rules correct that.
SKILL.md
delegation-triggers.SKILL.mdname: delegation-triggers
description: 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; these rules correct that.
Delegation Triggers
Opus 4.8 is documented to under-reach for subagents. Apply these rules instead of intuition.
Delegate (spawn subagents, in parallel where independent) when:
- Work fans out across **independent items**: reading/searching many files, auditing
several modules, running several independent investigations.
- You need a **broad search** where only the conclusion matters (use a read-only
explore subagent; you keep the answer, not the file dumps).
- You need **fresh-context verification** of your own work (see verification-loop).
- Two or more workstreams have **no shared state** and no ordering dependency — launch
them in one message so they run concurrently.
Work directly when:
- A single file read or a known-location lookup would answer the question.
- Edits are sequential and each depends on the previous result.
- The task is small enough that subagent setup costs more than it saves.
How
- Give each subagent a self-contained brief: goal, exact scope, what to return.
- Don't duplicate a delegated search yourself — wait for the result.
- Prefer asynchronous delegation: keep working on the main thread while subagents run;
intervene only if one goes off track.
Read more
name: delegation-triggers description: 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; these rules correct that.
Delegation Triggers
Opus 4.8 is documented to under-reach for subagents. Apply these rules instead of intuition.
Delegate (spawn subagents, in parallel where independent) when:
- Work fans out across **independent items**: reading/searching many files, auditing
several modules, running several independent investigations.
- You need a **broad search** where only the conclusion matters (use a read-only
explore subagent; you keep the answer, not the file dumps).
- You need **fresh-context verification** of your own work (see verification-loop).
- Two or more workstreams have **no shared state** and no ordering dependency — launch
them in one message so they run concurrently.
Work directly when:
- A single file read or a known-location lookup would answer the question.
- Edits are sequential and each depends on the previous result.
- The task is small enough that subagent setup costs more than it saves.
How
- Give each subagent a self-contained brief: goal, exact scope, what to return.
- Don't duplicate a delegated search yourself — wait for the result.
- Prefer asynchronous delegation: keep working on the main thread while subagents run;
intervene only if one goes off track.
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
Other skills on modelharness.
@vitaliikapliukView SkillSkill
verification-loop
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…
@vitaliikapliukView Skill