develop

A command for carrying out software-development tasks listed in a project’s task breakdown. It can choose the next ready task, run a numbered task, or work through all remaining tasks.

In plain words
What is it for?
Use it to implement planned features one task at a time, or to run a whole sequence of independent tasks with confirmation between them.
Why use it?
It removes the need to find the next unfinished task and check its prerequisites by hand. It also keeps task progress updated as work proceeds.

Command

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/funkyoz/funkyoz-plugins/develop
Clone the repo
git clone --depth 1 https://github.com/FunkyOz/funkyoz-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,095 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 $0.00011 $0.01095
Opus 5 $0.00005 $0.00548
Sonnet 5 $0.00002 $0.00219
Haiku 4.5 $0.00001 $0.00110

Measured yesterday against content hash 66283430265b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

develop 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.

software-engineer/commands/develop.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Develop Command

You are a senior software engineer executing development tasks according to the planned task breakdown.

Input

  • Argument: {{1}}
    • next (default) - Work on the next available todo task
    • [number] - Work on a specific task (e.g., 01, 05)
    • all - Work through all remaining tasks sequentially (with confirmation between tasks)

Prerequisites

Before starting, verify:

  1. A tasks/ directory exists in the project root
  2. The 00-index.md file exists
  3. Task files exist with proper format

If no task breakdown exists, inform the user:

"No task breakdown found. Please run /software-engineer:plan <feature description> first to create a development plan."

Development Workflow

Step 1: Select Task

Based on the argument:

  • If next: Find the first task with status: todo that has all dependencies marked as done
  • If [number]: Load that specific task file
  • If all: Start with the first available task

If the selected task has unmet dependencies, notify the user and suggest completing dependencies first.

Step 2: Begin Task

  1. Read the task file completely to understand requirements
  2. Update task status to progress:
    • Modify the YAML frontmatter: status: progress
  3. Update 00-index.md to reflect the status change
  4. Announce what you're working on:

    "Starting Task [XX]: [Title] Priority: [Priority] | Complexity: [Complexity]

    Objectives:

    • [objective 1]
    • [objective 2]"

Step 3: Analyze Project Context

Before implementing:

  1. Review existing code patterns and conventions
  2. Check related files that might be affected
  3. Understand the codebase architecture
  4. Identify integration points

Step 4: Implement the Task

Execute the implementation following:

  1. Follow project conventions - Match existing code style, naming conventions, and patterns
  2. Write clean code - Apply SOLID principles, DRY, and best practices
  3. Handle errors properly - Include appropriate error handling and validation
  4. Add comments - Document complex logic and public APIs
  5. Consider edge cases - Handle boundary conditions and invalid inputs

Read the full file on GitHub · 130 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 · 130 lines · 11 tokens per session scan A 66283430265b

Subscribe to this mod's changes

develop is a command published in the GitHub repository FunkyOz/funkyoz-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 1,095 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.