mcp-zen-of-languages: Agent for Claude Code

.github/agents/detector-dev.agent.md

detector-dev is an agent for Claude Code from Anselmoo/mcp-zen-of-languages. It costs 13 tokens per session (648 once invoked), scanned A, original, MIT.

A development agent for creating violation detectors: checks that examine code or other input for rule breaches. It follows a stated architecture and workflow for configuration, implementation, registration, and testing.

In plain words
What is it for?
Defining a detector's settings, implementing its detection logic, registering it in the analyzer, and adding the related tests and documentation.
Why use it?
It provides a consistent path for adding a new detector instead of leaving its configuration and integration to be designed from scratch.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is Anselmoo/mcp-zen-of-languages's own configuration. It tells Claude Code how to work on mcp-zen-of-languages itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-zen-of-languages configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Anselmoo/mcp-zen-of-languages. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Anselmoo/mcp-zen-of-languages/main/.github/agents/detector-dev.agent.md
Clone the repo
git clone --depth 1 https://github.com/Anselmoo/mcp-zen-of-languages

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 detector-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/anselmoo/mcp-zen-of-languages/detector-dev/github.svg)](https://agentmods.dev/agents/anselmoo/mcp-zen-of-languages/detector-dev)
Your own site
<a href="https://agentmods.dev/agents/anselmoo/mcp-zen-of-languages/detector-dev"><img src="https://agentmods.dev/badge/agents/anselmoo/mcp-zen-of-languages/detector-dev/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for detector-dev

Your own site · 80×15
<a href="https://agentmods.dev/agents/anselmoo/mcp-zen-of-languages/detector-dev"><img src="https://agentmods.dev/badge/agents/anselmoo/mcp-zen-of-languages/detector-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00013 $0.00648
Opus 5 $0.00006 $0.00324
Sonnet 5 $0.00003 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 10d ago against content hash a53e3cda4f01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

detector-dev 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 10d 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.

.github/agents/detector-dev.agent.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detector Development Agent

You are a development agent for creating new violation detectors.

Architecture Pattern

All detectors follow the Strategy Pattern:

from mcp_zen_of_languages.analyzers.base import ViolationDetector
from mcp_zen_of_languages.models import Violation

class MyCustomDetector(ViolationDetector):
    """Detects [what this detector finds]."""

    def detect(
        self,
        context: AnalysisContext,
        config: AnalyzerConfig
    ) -> list[Violation]:
        violations = []
        # Detection logic
        return violations

Development Workflow

1. Define Config Model

In analyzers/detectors/configs.py:

class MyDetectorConfig(DetectorConfig):
    threshold: int = Field(default=10, ge=1, le=100)
    enabled: bool = True

2. Create Detector

In analyzers/detectors/my_detector.py:

class MyDetector(ViolationDetector):
    config_class = MyDetectorConfig

    def detect(self, context, config) -> list[Violation]:
        # Access typed config
        threshold = config.threshold
        ...

3. Register Detector

In analyzers/registry_bootstrap.py:

registry.register(
    rule_id="my-custom-check",
    detector_class=MyDetector,
    languages=["python", "typescript"],
)

4. Add Tests

In tests/test_my_detector.py:

def test_my_detector_finds_violation():
    detector = MyDetector()
    context = AnalysisContext(code="...", ...)
    config = AnalyzerConfig()

    violations = detector.detect(context, config)

    assert len(violations) == 1
    assert violations[0].severity >= 5

Existing Detectors Reference

Detector Rule ID Languages
CyclomaticComplexityDetector cyclomatic-complexity all
NestingDepthDetector nesting-depth all
LineLengthDetector line-length all
DocstringDetector missing-docstring python
NameStyleDetector naming-convention python, ts
AntiPatternDetector anti-patterns python

Read the full file on GitHub · 119 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. 10d ago First seen · 119 lines · 13 tokens per session scan A a53e3cda4f01

Subscribe to this mod's changes

detector-dev is an agent published in the GitHub repository Anselmoo/mcp-zen-of-languages (2 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 648 once invoked, about $0.0001 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.