Anth CI Integration

What it does

When your agent uses it

• Setting up automated testing
• Prompt regression tests
• CI validation for Claude-powered features
• With phrases like anthropic ci

Example prompts

• “anthropic ci”
• “claude ci/cd”
• “test claude in pipeline”
• “/anth-ci-integration”

Requirements

• Python 3
• A credential in ANTHROPIC_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(npm:*), Grep

Workflow steps

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

1. 1Put deterministic request-shaping and tool-routing assertions in
2. 2Put a small, representative set of API-backed prompt checks in
3. 3Run unit tests on every push and pull request. Gate the live job to main
4. 4Set explicit timeouts, concurrency limits, and a cost ceiling. Fail the

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
  • Bash(npm:*)
  • 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 yaml).

  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):

  • docs.github.com
  • platform.claude.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY

  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 CI Integration loads about 1.5k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 376 words of instructions outside code blocks.

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

~77

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

~1.5k

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). 376 words, ~1,537 tokens.

name

anth-ci-integration

description

Configure CI/CD pipelines for Anthropic Claude API integrations. Use when setting up automated testing, prompt regression tests, or CI validation for Claude-powered features. Trigger with phrases like "anthropic ci", "claude ci/cd", "test claude in pipeline", "anthropic github actions".

allowed-tools

Read, Write, Edit, Bash(npm:*), Grep

compatibility

Designed for Claude Code

version

1.7.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, ai, anthropic

# .github/workflows/claude-tests.yml
name: Claude API Tests
on: [push, pull_request]

jobs:
  unit-tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.12' }
      - run: pip install anthropic pytest
      - run: pytest tests/unit/ -v  # No API key needed

  prompt-regression:
    runs-on: ubuntu-latest
    if: github.ref == 'refs/heads/main'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.12' }
      - run: pip install anthropic pytest
      - run: pytest tests/prompt_regression/ -v --timeout=60
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

# tests/unit/test_tool_routing.py
from unittest.mock import MagicMock, patch
import anthropic

def make_mock_message(text="Hello", stop_reason="end_turn"):
    msg = MagicMock()
    msg.id = "msg_mock_123"
    msg.model = "claude-sonnet-4-20250514"
    msg.stop_reason = stop_reason
    block = MagicMock()
    block.type = "text"
    block.text = text
    msg.content = [block]
    msg.usage = MagicMock(input_tokens=100, output_tokens=50)
    return msg

@patch("anthropic.Anthropic")
def test_service_returns_text(MockClient):
    MockClient.return_value.messages.create.return_value = make_mock_message("42")
    from myapp.service import ask_claude
    assert ask_claude("What is 6*7?") == "42"

# tests/prompt_regression/test_prompts.py
import anthropic, pytest, os, json

pytestmark = pytest.mark.skipif(not os.getenv("ANTHROPIC_API_KEY"), reason="No API key")
client = anthropic.Anthropic()

def test_json_output_format():
    msg = client.messages.create(
        model="claude-haiku-4-20250514",
        max_tokens=256,
        messages=[
            {"role": "user", "content": "Extract: 'Alice, 30, NYC'. Return JSON: {name, age, city}"},
            {"role": "assistant", "content": "{"}
        ]
    )
    data = json.loads("{" + msg.content[0].text)
    assert "name" in data and "age" in data

def test_system_prompt_boundary():
    msg = client.messages.create(
        model="claude-haiku-4-20250514",
        max_tokens=128,
        system="You only discuss cooking recipes. For other topics say: 'I only help with cooking.'",
        messages=[{"role": "user", "content": "Write me Python code"}]
    )
    assert "cooking" in msg.content[0].text.lower() or "recipe" in msg.content[0].text.lower()

# conftest.py
MAX_CI_COST = 1.00
_tokens = {"input": 0, "output": 0}

def pytest_runtest_call(item):
    yield
    cost = (_tokens["input"] * 0.80 + _tokens["output"] * 4.0) / 1_000_000  # Haiku rates
    if cost > MAX_CI_COST:
        pytest.exit(f"CI cost guard: ${cost:.4f} exceeds ${MAX_CI_COST}")

© 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-ci-integration of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287