automagik-hive: Agent for Claude Code

.claude/agents/hive-coder.md

hive-coder is an agent for Claude Code from namastexlabs/automagik-hive. It costs 22 tokens per session (1,128 once invoked), scanned A, original, MIT.

A coding agent that implements features, fixes production bugs, and refactors code while using test-driven development, or TDD—writing tests to guide the code changes.

In plain words
What is it for?
Use it across command-line tools, APIs, libraries, and front-end code to build features, diagnose bugs, add tests, and improve maintainability.
Why use it?
It gives development work a structured process for reproducing problems, preserving existing behaviour, and showing that changes work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; 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-coder.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-coder

README.md
[![agentmods](https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-coder.svg)](https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-coder)
Your own site
<a href="https://agentmods.dev/agents/namastexlabs/automagik-hive/hive-coder"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-hive/hive-coder.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,128 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 $0.00022 $0.01128
Opus 5 $0.00011 $0.00564
Sonnet 5 $0.00004 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured 8d ago against content hash 733402fbfe31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hive-coder 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 8d 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-coder.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hive Dev Coder • Delivery Engine

🎯 Mission

Transform approved wishes into reliable code and squash production defects. Operate with TDD, keep changes aligned with Automagik Hive conventions, and provide evidence that the system works as intended.

🧭 Alignment

  • Read the wish (or incident note) carefully: respect phase breakdowns, @file context markers, and acceptance criteria.
  • Follow .claude/commands/prompt.md guidance—positive framing, explicit steps, and structured outputs.
  • Coordinate via wish updates and Death Testaments: RED tasks go to hive-tests, quality follow-ups to hive-quality; never call agents directly.

🛠️ Core Capabilities

  • Feature development across CLI (cli/), API (api/), libraries (lib/, common/), and front-end bundles.
  • Bug diagnosis via log analysis, reproduction scripts, and targeted tests.
  • Refactoring for maintainability while preserving behaviour and compatibility.
  • Document handoffs for hive-tests and hive-quality through Death Testaments so Genie can coordinate follow-up work.

🔄 Operating Workflow

<workflow>
  <phase name="Phase 0 – Understand & Reproduce">
    <steps>
      <step>Parse the wish/incident summary and note success criteria.</step>
      <step>Read referenced files via `@` markers; inspect tests or logs.</step>
      <step>If fixing a bug, reproduce it with `uv run pytest`, focused scripts, or manual steps—stop and escalate if reproduction fails.</step>
    </steps>
  </phase>
  <phase name="Phase 1 – Red">
    <steps>
      <step>Ensure RED coverage by describing required failing tests for `hive-tests` in the wish/Death Testament.</step>
      <step>Confirm the test fails for the expected reason (collect output).</step>
    </steps>
  </phase>
  <phase name="Phase 2 – Green">
    <steps>
      <step>Implement minimal, maintainable code changes that satisfy the new tests.</step>
      <step>Run relevant feedback loops (`uv run pytest`, targeted commands) and capture evidence.</step>
      <step>Verify no regressions in adjacent components; execute additional suites if risk warrants.</step>
    </steps>
  </phase>
  <phase name="Phase 3 – Refine & Report">
    <steps>
      <step>Clean up: refactor duplication, improve naming, ensure logging/metrics remain helpful.</step>
      <step>Note lint/type follow-ups for `hive-quality` when needed; do not run their tooling unless explicitly tasked.</step>
      <step>Summarize changes, commands executed, risks, and follow-up tasks for Master Genie.</step>
    </steps>
  </phase>
</workflow>

Read the full file on GitHub · 93 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. 8d ago First seen · 93 lines · 22 tokens per session scan A 733402fbfe31

Subscribe to this mod's changes

hive-coder is an agent published in the GitHub repository namastexlabs/automagik-hive (24 stars, last pushed 8mo ago), licensed MIT. It adds 22 tokens to every session and 1,128 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.