Anth Cost Tuning

What it does

When your agent uses it

• Analyzing Claude API billing
• Implementing cost controls and budget alerts
• With phrases like anthropic cost
• Reduce claude spend

Example prompts

• “anthropic cost”
• “claude billing”
• “reduce claude spend”
• “/anth-cost-tuning”

Requirements

• Python 3
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Baseline request volume, input/output/cache tokens, latency, quality, and spend by feature using a redacted measurement window. Do not…
2. 2Define a quality floor and route only eligible workloads to the least expensive model that meets it. Use prompt caching only for approved…
3. 3Cap max_tokens, concurrency, retries, and batch size. Enforce per-feature and per-workspace budgets before requests are sent; fail closed…
4. 4Test the proposed policy on synthetic fixtures in a sandbox, then canary it with aggregate cost, quality, latency, error, and rate-limit…
5. 5If quality, spend, or policy thresholds regress, disable the new route/cache/batch policy, restore the prior configuration, and retain a…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • platform.claude.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Anth Cost Tuning loads about 2.1k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 527 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~89

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 527 words, ~2,065 tokens.

name

anth-cost-tuning

description

Optimize Anthropic Claude API costs with model routing, prompt caching, batching, and spend monitoring. Use when analyzing Claude API billing, reducing costs, or implementing cost controls and budget alerts. Trigger with phrases like "anthropic cost", "claude billing", "reduce claude spend", "anthropic budget", "claude pricing optimize".

allowed-tools

Read, Write, Edit, Grep

compatibility

Designed for Claude Code

version

1.7.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, ai, anthropic

def estimate_cost(
    input_tokens: int,
    output_tokens: int,
    model: str = "claude-sonnet-4-20250514",
    cached_input: int = 0,
    use_batch: bool = False
) -> float:
    pricing = {
        "claude-haiku-4-20250514": {"input": 0.80, "output": 4.00, "cache_read": 0.08},
        "claude-sonnet-4-20250514": {"input": 3.00, "output": 15.00, "cache_read": 0.30},
        "claude-opus-4-20250514": {"input": 15.00, "output": 75.00, "cache_read": 1.50},
    }
    rates = pricing[model]
    uncached_input = input_tokens - cached_input

    cost = (
        uncached_input * rates["input"] +
        cached_input * rates["cache_read"] +
        output_tokens * rates["output"]
    ) / 1_000_000

    if use_batch:
        cost *= 0.5

    return cost

# Example: 10K requests/day, 500 input + 200 output tokens each
daily = estimate_cost(500, 200, "claude-sonnet-4-20250514") * 10_000
print(f"Daily: ${daily:.2f}")      # ~$0.045 * 10K = $450/day
print(f"Monthly: ${daily * 30:.2f}")  # ~$13,500/month

# Same with Haiku + batching
daily_optimized = estimate_cost(500, 200, "claude-haiku-4-20250514", use_batch=True) * 10_000
print(f"Optimized: ${daily_optimized:.2f}/day")  # ~$22/day (20x cheaper)

def route_to_model(task: str, complexity: str) -> str:
    """Route tasks to cheapest adequate model."""
    # Haiku: classification, extraction, yes/no, routing ($0.80/$4)
    if task in ("classify", "extract", "route", "validate"):
        return "claude-haiku-4-20250514"

    # Sonnet: general tasks, code, tool use ($3/$15)
    if complexity in ("low", "medium"):
        return "claude-sonnet-4-20250514"

    # Opus: only for complex reasoning, research ($15/$75)
    return "claude-opus-4-20250514"

# Cache system prompts and reference documents (90% input savings)
# Break-even: 2 requests with same cached content
message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=256,
    system=[{
        "type": "text",
        "text": large_reference_document,  # 10K+ tokens
        "cache_control": {"type": "ephemeral"}
    }],
    messages=[{"role": "user", "content": user_question}]
)

# 50% cost reduction for anything that doesn't need immediate response
# Ideal for: summarization pipelines, data extraction, content generation
batch = client.messages.batches.create(requests=[...])  # Up to 100K requests

import anthropic
from dataclasses import dataclass, field

@dataclass
class SpendTracker:
    budget_usd: float = 100.0
    spent_usd: float = 0.0
    requests: int = 0

    def track(self, response):
        cost = estimate_cost(
            response.usage.input_tokens,
            response.usage.output_tokens,
            response.model,
            getattr(response.usage, "cache_read_input_tokens", 0)
        )
        self.spent_usd += cost
        self.requests += 1

        if self.spent_usd > self.budget_usd * 0.8:
            print(f"WARNING: 80% budget used (${self.spent_usd:.2f}/${self.budget_usd})")
        if self.spent_usd > self.budget_usd:
            raise RuntimeError(f"Budget exceeded: ${self.spent_usd:.2f}")

tracker = SpendTracker(budget_usd=50.0)

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/anth-cost-tuning of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287