Cost Advise
Optimisation findings from your own Claude Code and Codex logs — low cache hit ratio, 1-hour cach…
by ruvnet · MIT
The skill
Optimisation findings from your own Claude Code and Codex logs — low cache hit ratio, 1-hour cache writes that did not pay back, sub-agents on a top-tier model, Codex reasoning share, bloated sessions — each with evidence and a what-if saving. Use when asked how to cut spend or why it is high.
Cost Advise
node ${CLAUDE_PLUGIN_ROOT}/scripts/advise.mjs --since 7d
Rules for presenting findings
- Savings are what-if repricings of the same tokens at another rate. They say nothing about quality; tell the user to spot-check before switching a model.
- A finding with
saving n/ahas no defensible number (no measured delta exists). Do not invent one. - Do not change settings, models or CLAUDE.md on the user's behalf; present the action and let them choose.
- Prefer the largest controllable lever first: cache discipline, then model tier for sub-agents, then reasoning effort, then context size.
- Pair with
cost-ledgerfor the totals andcost-sessionto drill into one expensive session.
Use this skill
Connect your agent to the Skill Store MCP server and ask for it by ref: ruvnet/cost-advise-40376218247.
Details
- Publisher
- ruvnet
- Category
- AI & Agents › Model operations & inference
- License
- MIT
- Updated
- 2026-10-18
References
More from ruvnet
- Agent Adaptive Coordinator Coordinates swarm topology switching between hierarchical, mesh, ring and hybrid patterns using clau
- Agent Agent Goal-oriented action planning (GOAP) for multi-step objectives: models world state as preconditions
- Agent Agentic Payments Manages autonomous AI agent payments through the agentic-payments MCP server: creates and revokes Ac
- Agent Analyze Code Quality This skill analyzes source code in JavaScript, TypeScript, Python, Java, and Go files for quality is