Anth Performance Tuning

What it does

When your agent uses it

• Experiencing slow responses
• Optimizing token usage
• Reducing time-to-first-token in production
• With phrases like anthropic performance

Example prompts

• “anthropic performance”
• “claude speed”
• “optimize claude latency”
• “/anth-performance-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. 1Establish a baseline for time-to-first-token, completion latency, tokens, cache hit rate, throughput, quality, and errors using repeated…
2. 2Change one lever at a time: model, prompt/cache layout, token budget, streaming, batching, or concurrency. Keep prompt content out of logs…
3. 3Enforce request scope, max_tokens, timeout, retry, and concurrency limits. Stop the run when rate limits, quality, or data-policy checks…
4. 4Canary the selected configuration in a sandbox or internal workspace, compare against baseline, and obtain approval before production…
5. 5Restore the prior configuration on regression, invalidate temporary cache/test artifacts according to retention policy, 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 and typescript).

  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 Performance Tuning loads about 1.9k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 492 words of instructions outside code blocks.

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

~97

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

~1.9k

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). 492 words, ~1,948 tokens.

name

anth-performance-tuning

description

Optimize Claude API performance with prompt caching, model selection, streaming, and latency reduction techniques. Use when experiencing slow responses, optimizing token usage, or reducing time-to-first-token in production. Trigger with phrases like "anthropic performance", "claude speed", "optimize claude latency", "anthropic caching", "faster claude responses".

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

import anthropic

client = anthropic.Anthropic()

# Mark long, reusable content with cache_control
# Cached content: 90% cheaper on subsequent requests, near-zero latency for cached portion
message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": "You are an expert on the following 50-page document: ...<long document>...",
            "cache_control": {"type": "ephemeral"}  # Cache this block
        }
    ],
    messages=[{"role": "user", "content": "What does section 3.2 say?"}]
)

# Check cache performance
print(f"Cache read tokens: {message.usage.cache_read_input_tokens}")   # Free/cheap
print(f"Cache creation tokens: {message.usage.cache_creation_input_tokens}")  # First call only
print(f"Uncached input tokens: {message.usage.input_tokens}")

# Route by task complexity
def select_model(task_type: str) -> str:
    routing = {
        "classify": "claude-haiku-4-20250514",
        "extract": "claude-haiku-4-20250514",
        "summarize": "claude-sonnet-4-20250514",
        "code": "claude-sonnet-4-20250514",
        "research": "claude-opus-4-20250514",
    }
    return routing.get(task_type, "claude-sonnet-4-20250514")

# Streaming reduces time-to-first-token from seconds to ~200ms
with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=2048,
    messages=[{"role": "user", "content": prompt}]
) as stream:
    for text in stream.text_stream:
        yield text  # User sees response immediately

# 1. Set max_tokens to what you actually need (not max)
msg = client.messages.create(
    model="claude-haiku-4-20250514",
    max_tokens=128,  # Not 4096 — smaller = faster generation
    messages=[{"role": "user", "content": "Classify as positive/negative: 'Great product!'"}]
)

# 2. Use prefill to skip preamble
msg = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=64,
    messages=[
        {"role": "user", "content": "Classify sentiment: 'Great product!'"},
        {"role": "assistant", "content": "Sentiment:"}  # Skip "Sure, I'd be happy to..."
    ]
)

# 3. Pre-check token count for large inputs
count = client.messages.count_tokens(
    model="claude-sonnet-4-20250514",
    messages=[{"role": "user", "content": large_document}]
)
if count.input_tokens > 100_000:
    # Chunk or summarize first
    pass

import Anthropic from '@anthropic-ai/sdk';
import PQueue from 'p-queue';

const client = new Anthropic();
const queue = new PQueue({ concurrency: 10 });

// Process multiple prompts in parallel (within rate limits)
const results = await Promise.all(
  prompts.map(p => queue.add(() =>
    client.messages.create({
      model: 'claude-haiku-4-20250514',
      max_tokens: 256,
      messages: [{ role: 'user', content: p }],
    })
  ))
);

© 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-performance-tuning of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287