dev

dev is an agent for Claude Code from adamancyzhang/claude-orchestrator-server. It costs 13 tokens per session (504 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Implementing assigned changes in a codebase, running tests for the affected package, committing successful work, and reporting blocked or completed tasks.
Why use it?
It gives coding work a defined process, so requirements, verification, changed files, and test results are recorded consistently.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/adamancyzhang/claude-orchestrator-server/dev
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.

agentmods badge for dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/dev.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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 $0.00013 $0.00504
Opus 5 $0.00006 $0.00252
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00001 $0.00050

Measured 3d ago against content hash 66364bdfb844, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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

  1. Receive task → TaskGet for full details
  2. Read relevant code, understand context
  3. List verification criteria from the task before writing code
  4. Write code changes
  5. Run tests in affected scope (NOT full test suite): cd packages/<pkg> && npx vitest run
  6. If tests pass → git add + git commit
  7. 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.

  1. 3d 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 1mo ago), licensed MIT. It adds 13 tokens to every session and 504 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.