dev-cycle

A development workflow that alternates between a developer agent, which implements requirements, and a reviewer agent, which critiques the result. The cycle repeats until the reviewer approves the work.

In plain words
What is it for?
Reading project requirements, coordinating implementation and review, sending feedback back to the developer, and stopping when the change is approved.
Why use it?
It creates a defined review loop so implementation issues can be identified and corrected before the work is considered finished.

Command 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 commands/entireio/cli/dev-cycle
Clone the repo
git clone --depth 1 https://github.com/entireio/cli

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 942 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 $0.00016 $0.00942
Opus 5 $0.00008 $0.00471
Sonnet 5 $0.00003 $0.00188
Haiku 4.5 $0.00002 $0.00094

Measured yesterday against content hash 0a0c9c8f8959, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-cycle 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 yesterday.

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/commands/dev-cycle.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Cycle Orchestrator

You are orchestrating a development cycle between a Developer agent and a Code Reviewer agent. Your job is to manage the back-and-forth until the implementation is complete and approved.

The Cycle

┌─────────────────┐
│   Requirements  │
└────────┬────────┘
         │
         ▼
┌─────────────────┐
│    Developer    │◄─────────┐
│   Implements    │          │
└────────┬────────┘          │
         │                   │
         ▼                   │
┌─────────────────┐          │
│    Reviewer     │          │
│    Critiques    │          │
└────────┬────────┘          │
         │                   │
         ▼                   │
    ┌─────────┐              │
    │Approved?│──── No ──────┘
    └────┬────┘
         │ Yes
         ▼
┌─────────────────┐
│      Done       │
└─────────────────┘

Agent Instructions

  • Developer: .claude/agents/dev.md
  • Reviewer: .claude/agents/reviewer.md

Your Process

Phase 1: Setup

  1. Read the requirements from: $ARGUMENTS/README.md
  2. Understand what needs to be built
  3. Create feature branch (if not already on one):
    # Extract feature name from path (e.g., "jaja-bot" from "docs/requirements/jaja-bot")
    git checkout -b feature/[feature-name]
    
  4. Review any existing task files and review files in $ARGUMENTS/

Phase 2: Development Loop

For each iteration:

  1. Invoke Developer Agent Use the Task tool:

    Task(
      subagent_type: "general-purpose",
      prompt: "
        Read and follow .claude/agents/dev.md
    
        Requirements folder: $ARGUMENTS
        Previous reviewer feedback: [paste feedback if any, or 'None - first iteration']
    
        Implement the next increment using TDD.
        Report what you built when done.
      "
    )
    
  2. Invoke Reviewer Agent Use the Task tool:

    Task(
      subagent_type: "general-purpose",
      prompt: "
        Read and follow .claude/agents/reviewer.md
    
        Requirements folder: $ARGUMENTS
    
        Review the branch changes (git diff main...HEAD -- . ':!.entire').
        Provide structured feedback with verdict: APPROVE or REQUEST CHANGES
      "
    )
    

Read the full file on GitHub · 131 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. yesterday First seen · 131 lines · 16 tokens per session scan A 0a0c9c8f8959

Subscribe to this mod's changes

dev-cycle is a command published in the GitHub repository entireio/cli (5,038 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 942 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.