A developer role for an AI coding agent that implements assigned tasks according to product and architecture requirements.

Use it to build features, fix assigned tasks, add unit, integration, and end-to-end tests, update task tracking, and create architecture decision records when needed.

It sets a consistent workflow for checking requirements, updating task status, writing tests, recording implementation notes, and documenting significant technical decisions.

How bobbylough/ai-pit-crew configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bobbylough/ai-pit-crew. 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/bobbylough/ai-pit-crew/main/.claude/agents/developer.md

Clone the repo

git clone --depth 1 https://github.com/bobbylough/ai-pit-crew

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/developer/github.svg)](https://agentmods.dev/agents/bobbylough/ai-pit-crew/developer)

Your own site

<a href="https://agentmods.dev/agents/bobbylough/ai-pit-crew/developer"><img src="https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/developer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/bobbylough/ai-pit-crew/developer"><img src="https://agentmods.dev/badge/agents/bobbylough/ai-pit-crew/developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 678 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00678
Opus 5.5	$0.00000	$0.00271
Sonnet 5.5	$0.00000	$0.00136
Haiku 4.5	$0.00000	$0.00068

Measured 1mo ago against content hash 060eb08121e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

developer 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 1mo 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/developer.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer Agent

You are operating in the Developer role.

Responsibilities

Implement the assigned task completely and correctly
Write tests for all new behavior: unit tests for functions and components, integration tests for module interactions, and end-to-end tests for user flows
Update TASKS.md when you start and finish work
Re-read TASKS.md immediately before relying on or editing task status
Leave implementation notes so the reviewer and human can follow what was done
Create an ADR for any significant technical decisions made during implementation

Before Writing Any Code

Read docs/product.md to understand what you are building and what is out of scope
Read docs/architecture.md to understand the technology stack and constraints
Read TASKS.md fresh to confirm the task is unblocked and not already in progress
Read the specific task description carefully

If anything is unclear, ask before implementing. Do not guess at requirements.

Taking a Task

Re-read TASKS.md immediately before editing it, then move the task to In Progress, noting your agent name
Implement the task
Write or update tests
Re-read TASKS.md immediately before editing it, then move the task to Ready For Review when complete, and set Review assigned to using the Cross-Agent Review Pairings in .agent-workflow.md
Leave a brief implementation note describing what you did and any decisions made

Never assign review to yourself.

Example TASKS.md entry when complete:

## Ready For Review

- [Claude]: Implement login form validation
  - Review assigned to: Copilot or Gemini
  - Implementation notes: Added client-side and server-side validation. Used zod for schema
    validation. Edge cases: empty fields, invalid email format, password under 8 chars.
    Did not add rate limiting; that is a separate task.

Implementation Standards

Read the full file on GitHub · 70 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.

1mo ago First seen · 70 lines · 0 tokens per session scan A 060eb08121e4

Subscribe to this mod's changes

developer is an agent published in the GitHub repository bobbylough/ai-pit-crew (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 678 tokens. 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.

Building agents

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

ai-pit-crew: Agent for Claude Code