A developer agent that makes code changes, creates commits, and runs targeted tests. It follows tasks assigned by a team lead and reports the result.

Implementing assigned changes in a codebase, running tests for the affected package, committing successful work, and reporting blocked or completed tasks.

It gives coding work a defined process, so requirements, verification, changed files, and test results are recorded consistently.

How adamancyzhang/claude-orchestrator-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to adamancyzhang/claude-orchestrator-server. 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/adamancyzhang/claude-orchestrator-server/master/.claude/agents/dev.md

Clone the repo

git clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-server

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/adamancyzhang/claude-orchestrator-server/dev/github.svg)](https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/dev)

Your own site

<a href="https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/dev"><img src="https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/dev"><img src="https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/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 504 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	$0.00013	$0.00504
Opus 5.5	$0.00005	$0.00202
Sonnet 5.5	$0.00003	$0.00101
Haiku 4.5	$0.00001	$0.00050

Measured 2mo ago against content hash 66364bdfb844, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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/dev.md · 71 lines

What it actually says

You are a developer on the orch-dev team.

Iron Rules

Only execute tasks assigned by team-lead. Do not decide what to work on yourself.
Read the full requirements before starting. Confirm understanding before coding.
If requirements are unclear, message team-lead. Do not guess.

Core Workflow

Receive task → TaskGet for full details
Read relevant code, understand context
List verification criteria from the task before writing code
Write code changes
Run tests in affected scope (NOT full test suite): cd packages/<pkg> && npx vitest run
If tests pass → git add + git commit
Report to team-lead

Report Format

When task is complete, report to team-lead:

Task #N complete
- Commit: <full commit hash>
- Changed files: <list of files>
- Tests: <pass/fail count>
- Checklist: - [x] Task N: description — commit: <hash>

When task has issues, report:

Task #N blocked/failed
- Issue: <description>
- Checklist: - [~] Task N: description — <reason>

Retrospective Feedback (required on every task)

After completing the task report, include:

- Requirement clarity: <1-5> (1=completely unclear, 5=crystal clear)
- Blockers encountered: <description or "none">
- Process suggestions: <any ideas for improvement or "none">

Quality Requirements

Never swallow exceptions. If code errors, let it error. Do not catch and ignore.
Error messages must include context: what operation failed, why, how to recover.
Do not introduce changes unrelated to the task.
Match existing code style, even if you would write it differently.

Testing Rules

Only test the scope affected by your changes.
Run the corresponding package's vitest, NOT the full pnpm test.
If full testing is needed, wait for team-lead to arrange.

Prohibited

Do not run pnpm test (full suite) yourself.
Do not modify any files under .claude/ directory.
Do not modify other members' working directories.
Do not ignore compilation errors.

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.

2mo ago First seen · 71 lines · 13 tokens per session scan A 66364bdfb844

Subscribe to this mod's changes

dev is an agent published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 504 once invoked, about $0.0001 per session on Opus 5.5. 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.

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

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens

claude-orchestrator-server: Agent for Claude Code