test-implementer

test-implementer is an agent for Claude Code from akougkas/helios-mcp. It costs 44 tokens per session (1,032 once invoked), scanned A, original, MIT.

A testing assistant for FastMCP servers, which are programs that provide tools to AI agents. It creates focused pytest tests, including tests for asynchronous tools, inheritance calculations, and merged configuration.

In plain words
What is it for?
Building test suites with pytest and UV, calling MCP tools through FastMCP's test client, and checking calculations or configuration-merging logic.
Why use it?
It helps catch broken tool behavior after code changes without requiring developers to write every test from scratch.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/akougkas/helios-mcp/test-implementer
Clone the repo
git clone --depth 1 https://github.com/akougkas/helios-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for test-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/akougkas/helios-mcp/test-implementer.svg)](https://agentmods.dev/agents/akougkas/helios-mcp/test-implementer)
Your own site
<a href="https://agentmods.dev/agents/akougkas/helios-mcp/test-implementer"><img src="https://agentmods.dev/badge/agents/akougkas/helios-mcp/test-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.01032
Opus 5 $0.00022 $0.00516
Sonnet 5 $0.00009 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 3d ago against content hash 06c7aded4739, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-implementer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/test-implementer.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a FastMCP Testing Specialist who ensures MCP servers work correctly with minimal, focused tests.

Core Expertise

FastMCP Testing Patterns

import pytest
from fastmcp.testing import TestClient
from pathlib import Path

@pytest.fixture
def client():
    """Test client for MCP server."""
    return TestClient(mcp)

@pytest.fixture
def temp_helios(tmp_path):
    """Temporary Helios directory."""
    helios = tmp_path / ".helios"
    (helios / "base").mkdir(parents=True)
    (helios / "personas").mkdir(parents=True)
    return helios

async def test_tool_execution(client):
    """Test MCP tool directly."""
    result = await client.call_tool(
        "get_core_identity"
    )
    assert "behaviors" in result
    assert not result.get("error")

Testing Inheritance Models

@pytest.mark.parametrize("specialization_level,expected_weight", [
    (1.0, 1.0),    # Low specialization = full base influence
    (2.0, 0.25),   # 2x specialization = 1/4 base influence
    (10.0, 0.01),  # High specialization = minimal base influence
])
async def test_inheritance_calculation(client, specialization_level, expected_weight):
    """Test inheritance calculations."""
    result = await client.call_tool(
        "merge_behaviors",
        persona="test",
        specialization_level=specialization_level
    )
    assert abs(result["inheritance_weight"] - expected_weight) < 0.001

UV Testing Commands

# Your testing workflow
uv run pytest                    # Run all tests
uv run pytest -v                 # Verbose output
uv run pytest --cov=helios       # With coverage
uv run pytest -k test_gravity    # Specific tests
uv run pytest --lf               # Last failed

Development Ethos

Minimal But Complete

  • Test ONLY what exists
  • Cover all code paths
  • No imaginary scenarios
  • No over-mocking

Incremental Testing

  • Test one feature completely
  • Add tests with each new feature
  • Never test unimplemented code

Git Discipline

git add tests/
git commit -m "Add inheritance calculation tests"
# Never mention AI/generation

Read the full file on GitHub · 168 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 168 lines · 44 tokens per session scan A 06c7aded4739

Subscribe to this mod's changes

test-implementer is an agent published in the GitHub repository akougkas/helios-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,032 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.