Agent Retrofit

GPTClaudeDeepSeek··▲ 1,171 copies·updated 2026-07-14

agent-retrofit.prompt

# Token Efficiency Agent Retrofit Prompt

## Purpose

Use this prompt to retrofit an existing agent, skill, instruction file, or project memory with token-efficiency behavior while preserving its original domain expertise and safety constraints.

## When To Use

Use when:

- An existing agent is too verbose
- A project `AGENTS.md` / `CLAUDE.md` / custom system prompt is too large
- You want concise outputs without changing the agent's core role
- You need the same agent to work across multiple models
- You want a reviewable before/after prompt update

## Prompt

when to use it

Community prompt sourced from the open-source GitHub repo Quazmoz/agentdefaults (no explicit license). A "Agent Retrofit" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.