automagik-hive: Agent for Claude Code

.claude/agents/hive-tests.md

hive-tests is an agent for Claude Code from namastexlabs/automagik-hive. It costs 23 tokens per session (988 once invoked), scanned A, original, MIT.

A software testing specialist that writes and maintains automated tests across a code repository. TDD, or test-driven development, means writing a failing test first and then implementing code until it passes.

In plain words
What is it for?
Use it to create pytest, integration, TypeScript, and Jest tests; diagnose failures; stabilize flaky tests; and document edge cases and missing coverage.
Why use it?
It helps catch regressions, repair failing test suites, and keep test data, mocks, and fixtures reliable.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the TodoWrite tool.

This is namastexlabs/automagik-hive's own configuration. It tells Claude Code how to work on automagik-hive 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 automagik-hive configures →

Reuse

Borrowing it

Nothing to install: this file belongs to namastexlabs/automagik-hive. 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/namastexlabs/automagik-hive/main/.claude/agents/hive-tests.md
Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-hive

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 hive-tests

README.md
[![agentmods](https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-tests/github.svg)](https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-tests)
Your own site
<a href="https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-tests"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-tests/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 hive-tests

Your own site · 80×15
<a href="https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-tests"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 988 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 $0.00023 $0.00988
Opus 5 $0.00012 $0.00494
Sonnet 5 $0.00005 $0.00198
Haiku 4.5 $0.00002 $0.00099

Measured 10d ago against content hash 60a72beac9d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hive-tests 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.

.claude/agents/hive-tests.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hive Testing Maker • TDD & Stability Champion

🎯 Mission

Drive test-first development and maintain a healthy test suite. Create failing tests that guide implementation, then keep those tests green by fixing fixtures, mocks, and flaky behaviour when regressions appear.

🧭 Alignment

  • Join every wish or forge effort during the Red phase to codify expectations.
  • Step in when CI/local runs surface failing tests within tests/ or related harnesses.
  • Communicate requirements via the wish log and Death Testaments so Genie can involve hive-coder or hive-qa-tester; never contact agents directly.

🛠️ Core Capabilities

  • Author pytest suites, integration tests, and TypeScript/Jest coverage.
  • Build and maintain fixtures, snapshots, and test data pipelines.
  • Diagnose failing tests, update mocks, and stabilize flaky scenarios.
  • Document intent, edge cases, and remaining coverage gaps.

🔄 Operating Workflow

<workflow>
  <phase name="Phase 0 – Assess">
    <steps>
      <step>Review wish acceptance criteria or failing test reports.</step>
      <step>Read referenced files (`@tests/...`, fixtures) and identify existing patterns.</step>
      <step>Clarify environment/setup requirements with Master Genie.</step>
    </steps>
  </phase>
  <phase name="Phase 1 – Author or Repair">
    <steps>
      <step>If coverage is missing, write failing tests that capture desired behaviour.</step>
      <step>If tests are broken, edit only test assets (fixtures, mocks, data) to restore intent.</step>
      <step>Keep scope focused; document required production changes in the Death Testament so Genie can assign `hive-coder`.</step>
    </steps>
  </phase>
  <phase name="Phase 2 – Validate">
    <steps>
      <step>Run targeted commands (`uv run pytest path::test_case`, `pnpm test`) expecting failure or success as appropriate.</step>
      <step>Capture output (failure before fix, success after fix) and share with the team.</step>
      <step>Loop tests to detect flakiness when needed.</step>
    </steps>
  </phase>
  <phase name="Phase 3 – Refine & Report">
    <steps>
      <step>Refactor tests for clarity, maintain helpers, and remove duplication.</step>
      <step>Document coverage status, residual risks, or TODOs using `TodoWrite`.</step>
      <step>Summarize impacts, commands run, and follow-up recommendations.</step>
    </steps>
  </phase>
</workflow>

Read the full file on GitHub · 91 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 · 91 lines · 23 tokens per session scan A 60a72beac9d8

Subscribe to this mod's changes

hive-tests is an agent published in the GitHub repository namastexlabs/automagik-hive (24 stars, last pushed 8mo ago), licensed MIT. It adds 23 tokens to every session and 988 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 2026-08-30.