subagent-brief

Compress subagent prompts into ≤200-word briefs using a five-rule template.

231|24|Updated Apr 11, 2026

Search Tags:#optimization #LLM #multi-agent #orchestration #subagent #token-cost #prompt-brief

Ready to run

npx skills add https://github.com/LichAmnesia/lich-skills --skill subagent-brief

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-brief
Source: https://github.com/LichAmnesia/lich-skills/tree/main/skills/subagent-brief
Command: npx skills add https://github.com/LichAmnesia/lich-skills --skill subagent-brief

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compressing subagent prompts before spawning to minimize token costs and avoid token-bleed in multi-agent workflows.

Core Features & Use Cases

Pre-flight discipline for subagents: five rules to trim context and avoid token waste.
Structured brief template: ROLE, GOAL, INPUTS, CONSTRAINTS, RETURN.
Guidance on when to apply subagents and when not to use them in orchestration tasks.

Quick Start

Spawn a subagent only after generating a ≤200-word brief that follows the five rules and the brief template.

Frequently Asked Questions about subagent-brief

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reduce token cost when spawning multi-agent subagents in LLM workflows?▼

To reduce token cost in multi-agent LLM workflows, compress every subagent prompt into a ≤200-word brief using a structured template to strip redundant context and prevent token-bleed.

What is subagent prompt compression and how does it save tokens?▼

Subagent prompt compression is a pre-flight discipline that replaces files with paths and context with summaries, generating a concise brief to minimize token waste before launching subagents.

How do I write a structured subagent brief for LLM orchestration?▼

Write a structured subagent brief by applying five rules to strip context, replace files with paths, and compress text into a ≤200-word block containing ROLE, GOAL, INPUTS, CONSTRAINTS, and RETURN sections.

When should I not use subagents in multi-agent orchestration tasks?▼

You should avoid using subagents when a fan-out check indicates unnecessary complexity, ensuring you only spawn subagents for orchestration tasks that strictly require distributed processing.

Does multi-agent LLM orchestration require strict prompt length limits for subagents?▼

Multi-agent LLM orchestration benefits from strict prompt limits by compressing subagent briefs to ≤200 words, which minimizes token costs and ensures consistent, testable task briefing.

Why does spawning subagents with full context cause token-bleed in LLM workflows?▼

Spawning subagents with full context causes token-bleed because redundant information accumulates across multi-agent calls, making prompt compression necessary to eliminate wasted tokens.