by PromptSpace
Reduce Manus v5 credit consumption by 30-75% through intelligent task routing and autonomous strategy selection.
Free
One-time purchase
Strategy: DECOMPOSE_CASCADE Recommended Model: Manus 1.6 Standard Directives applied: Context Hygiene, 3-variant Batch Research. Estimated Credit Savings: 62% Analysis: Task is factual research plus file generation. Planning moved to Chat Mode (Free). Final asset via Agent Mode.
by PromptSpace
Reduce Manus v5 credit consumption by 30-75% through intelligent task routing and autonomous strategy selection.
Free
One-time purchase
⚡ Skill ready to install in Claude Code, Gemini CLI, or any MCP-compatible client. Read the install guides →
Strategy: DECOMPOSE_CASCADE Recommended Model: Manus 1.6 Standard Directives applied: Context Hygiene, 3-variant Batch Research. Estimated Credit Savings: 62% Analysis: Task is factual research plus file generation. Planning moved to Chat Mode (Free). Final asset via Agent Mode.
The Credit Optimizer v5 is a specialized middleware layer for the Manus v5 platform designed to slash operational costs by 30-75% while maintaining 100% quality parity. It acts as an intelligent router and task architect, analyzing user prompts before execution to determine the most cost-efficient path forward.
Standard LLM prompting often wastes credits on "thinking tokens" for simple tasks or forces high-cost models onto low-complexity queries. This skill implements "Context Hygiene" and smart batching to ensure you only pay for the intelligence you actually need. Audited across 53 scenarios, it includes 12 specific vulnerability fixes to prevent code degradation or shallow outputs.
mkdir -p ~/.claude/skills/credit-optimizer-v5 && curl -s -X POST 'https://api.promptspace.in/api/skills/credit-optimizer-v5/install' | python3 -c "import sys,json; sys.stdout.write(json.load(sys.stdin).get('installInstructions') or '')" > ~/.claude/skills/credit-optimizer-v5/SKILL.mdFree skills install directly. Paid skills require purchase - use the download button above after buying.
Security Scanned
Passed automated security review
No special permissions declared or detected
OpenClaw, Cursor, Claude Code, Codex CLI
PromptSpace
We build AI agent skill packages for content creators. Specializing in Chinese social media automation.