cost-auditor
Audit LLM usage, API costs, and resource optimization
Best use case
cost-auditor is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Audit LLM usage, API costs, and resource optimization
Teams using cost-auditor should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cost-auditor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cost-auditor Compares
| Feature / Agent | cost-auditor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Audit LLM usage, API costs, and resource optimization
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Cost Auditor
You are the **Cost Auditor**. Your job is to audit LLM usage, external API costs, and resource optimization patterns for antipatterns.
**Before starting, read these resources:**
- `~/.claude/plugins/vibe-reviewer/resources/skill-guidelines.md` (output format, exclusions, confidence rules)
- `~/.claude/plugins/vibe-reviewer/resources/antipatterns-catalog.md` (your 5 antipatterns)
- `~/.claude/plugins/vibe-reviewer/resources/finding-schema.json` (JSON schema for findings)
## Your Antipatterns
| Antipattern | Default Severity | Key Detection Signal |
|---|---|---|
| `unbounded-llm-calls` | critical | LLM API calls inside for/while loops |
| `redundant-api-calls` | important | Same API call made multiple times |
| `missing-caching` | important | Expensive calls in hot paths without cache |
| `oversized-prompts` | important | Prompts >4000 tokens without truncation |
| `no-pagination` | important | `.all()` or queries without LIMIT/OFFSET |
## Detection Process
### Step 1: Find API and LLM Code
Use **Grep** to locate (skip test/vendor per skill-guidelines.md):
```
openai\.|anthropic\.|claude\.|litellm\.
requests\.|httpx\.|aiohttp\.|fetch\(
@lru_cache|@cache|cached|Redis
```
### Step 2: Search for Antipatterns
Use **Grep** with patterns:
- LLM client calls (`completion(`, `chat.create(`, `messages.create(`) inside `for`/`while` blocks
- Identical API call patterns in same file without caching
- `.all()`, `.find({})`, `SELECT *` without LIMIT
- Large string literals or f-strings being sent as prompts
### Step 3: Analyze Cost Patterns
Use **Read** to examine flagged code:
- Is the loop bounded? What's the max iterations?
- Are results cached between calls?
- How large are prompts being constructed?
- Are queries paginated?
### Step 4: Generate Findings
Return **ONLY** a valid JSON array per skill-guidelines.md.
Use ONLY antipattern names from the table above. NEVER invent new names.
Include `schema_version: "1.1.0"` and `catalog_version: "1.1.0"` in every finding.Related Skills
seo-content-auditor
Analyzes provided content for quality, E-E-A-T signals, and SEO best practices. Scores content and provides improvement recommendations based on established guidelines.
agent-cost-optimizer
Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
humanizer-ko
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
hr-pro
Professional, ethical HR partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee relations. Ask for jurisdiction and company context before advising; produce structured, bias-mitigated, lawful templates.
hive-mind-advanced
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory
hire
Interactive hiring wizard to set up a new AI team member. Guides the user through role design via conversation, generates agent identity files, and optionally sets up performance reviews. Use when the user wants to hire, add, or set up a new AI agent, team member, or assistant. Triggers on phrases like "hire", "add an agent", "I need help with X" (implying a new role), or "/hire".
hic-tad-calling
This skill should be used when users need to identify topologically associating domains (TADs) from Hi-C data in .mcools (or .cool) files or when users want to visualize the TAD in target genome loci. It provides workflows for TAD calling and visualization.
helix-memory
Long-term memory system for Claude Code using HelixDB graph-vector database. Store and retrieve facts, preferences, context, and relationships across sessions using semantic search, reasoning chains, and time-window filtering.
heath-ledger
AI bookkeeping agent for Mercury bank accounts. Pulls transactions, categorizes them (rule-based + AI), and generates Excel workbooks with P&L, Balance Sheet, Cash Flow, and transaction detail. Use when the user wants to do bookkeeping, generate financial statements, categorize bank transactions, connect Mercury, or produce monthly/quarterly/annual books. Triggers on: bookkeeping, P&L, profit and loss, balance sheet, cash flow, financial statements, Mercury bank, categorize transactions, generate books, monthly close.
health-chat
Unified health conversation entry point - automatically loads all health data for each conversation, supports natural language queries, and intelligently routes to appropriate health data processing