Is the Delegation Triggers skill free?

Yes. The skill itself is free from vitaliikapliuk/modelharness. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Delegation Triggers SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Delegation Triggers?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Delegation Triggers with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Delegation Triggers

Explicit rules for when to spawn subagents vs. work directly, tuned against a 408-run benchmark.

by vitaliikapliuk · vitaliikapliuk/modelharness

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · f4ccf89

Applied to a real fan-out-or-not decision (12 independent auth-check files vs. one date-parsing function), it produced a decisive split -- parallel audit subagents for the files, direct work for the single function -- where unguided judgment just hedged; its 'Opus 4.8 under-delegates' claim checks out against the repo's own published 408-run benchmark table.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Delegation Triggers does

A short decision heuristic for agentic coding sessions: fan work out to parallel subagents when items are independent, a broad search only needs its conclusion, or fresh-context verification is needed; otherwise work directly. Triggers whenever an agent (or its user) is deciding whether a task is worth delegating -- multi-file audits, broad research, verification passes -- rather than defaulting to intuition. Pairs with a sibling 'verification-loop' skill in the same repo.

How to install Delegation Triggers

git clone https://github.com/vitaliikapliuk/modelharness
cd modelharness
mkdir -p ~/.claude/skills
cp -r skills/delegation-triggers ~/.claude/skills/delegation-triggers

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Delegation Triggers

/delegation-triggers Explicit rules for when to spawn subagents vs. work directly, tuned against a 408-run benchmark.

It also activates on plain-language prompts like these:

Should I spawn parallel subagents for these fifteen config files?
Is this task worth delegating, or should I just do it myself?
We have twelve independent audits, worth fanning out to agents?

Frequently asked questions

Is the Delegation Triggers skill free?: Yes. The skill itself is free from vitaliikapliuk/modelharness. SkillProof publishes the install command and an independent test verdict at no cost.
Does Delegation Triggers work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Applied to a real fan-out-or-not decision (12 independent auth-check files vs. one date-parsing function), it produced a decisive split -- parallel audit subagents for the files, direct work for the single function -- where unguided judgment just hedged; its 'Opus 4.8 under-delegates' claim checks out against the repo's own published 408-run benchmark table.
What is the Delegation Triggers SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Delegation Triggers?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Delegation Triggers with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.