Cost Plan — Security skill for Claude Code
LLM cost guardrails & quota-abuse audit — plan only, no limits added until approved.
How to install Cost Plan
Installs to ~/.claude/skills/kensaurus-cursor-kenji-cost-plan/SKILL.md
mkdir -p ~/.claude/skills/kensaurus-cursor-kenji-cost-plan && curl -fsSL https://raw.githubusercontent.com/kensaurus/cursor-kenji/HEAD/commands/cost-plan.md -o ~/.claude/skills/kensaurus-cursor-kenji-cost-plan/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Cost Plan does
description: "LLM cost guardrails & quota-abuse audit — plan only, no limits added until approved" argument-hint: "[path or scope]"
LLM Cost Guardrails Plan
Run the **`plan-llm-cost-guardrails`** skill: audit an LLM-powered app for runaway-cost and quota-abuse risk (unbounded loops, missing per-user limits, no budget caps), then produce a guardrail plan. **Audit and plan only — add no limits until the plan is approved.**
Emit findings ranked by severity with concrete `file:line` loc
Alternatives in Security
- Free Code — The free build of Claude Code 8.1k ★
- Skills Audit Report — Date: 2026-02-15 Auditor: Automated Skill Quality Audit Scope: Recently added skills in business-growth/, fina 5.3k ★
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Aeo Plan
Answer-engine / AEO & GEO citation-readiness audit — plan only, no edits until approved
Aso Plan
App Store / Play listing ASO audit — plan only, no metadata or screenshot edits until approved
Deadcode Plan
Dead-code audit — configured Knip baseline plus ratchet plan, delete nothing until approved
LLM Security
AI/LLM agent security audit (OWASP GenAI/LLM Top 10 2026): prompt injection (direct + indirect/RAG), jailbreak
Claude Bootstrap
Opinionated project initialization with security-first guardrails, spec-driven atomic todos, LLM testing patte
Security Playbook
Security skill pack for AI coding agents — behavioral guardrails, OWASP code/LLM rules, static analysis guidan
Related Agents
LLM Sec Review
LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode
Ad Exploit Operator
Executes ONE exploitation step from an approved attack plan in an authorized Active Directory assessment, invo
Plan
Triage, analyze, and create phased development plans. Iterate with the user until the plan is approved.
