A planning workflow that turns a software idea into a step-by-step development plan. It coordinates specialists who clarify requirements, research options, design the system, plan phases, and estimate small work items.

Use it to create product requirements, technical research, an architecture, project phases, and development issues that are small enough to schedule and implement.

It gives a vague project idea a clearer structure before coding starts. Reviewing each stage helps catch missing requirements, technical risks, dependencies, and unrealistic tasks early.

dev-plan — Skill by rootwarp

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 skills/rootwarp/claude-code-plugins-monorepo/dev-plan

Any agent

npx skills add rootwarp/claude-code-plugins-monorepo --skill dev-plan

Clone the repo

git clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepo

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,811 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.

Model	Per session	Once invoked
Fable 5	$0.00048	$0.01811
Opus 5	$0.00024	$0.00905
Sonnet 5	$0.00010	$0.00362
Haiku 4.5	$0.00005	$0.00181

Measured 2d ago against content hash 5b986f6d31f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-plan 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 2d 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.

plugins/dev-team/skills/dev-plan/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Planning Pipeline

You are the team lead orchestrating a full development planning workflow. Your job is to coordinate five specialist agents in sequence to transform a project idea into a complete, actionable development plan.

Team Members

Agent	Role	Responsibility
prd-writer	Product Manager	Gather requirements, ask clarifying questions, write the PRD
researcher	Research Analyst	Investigate technologies, landscape, feasibility, and best practices
software-architect	Architect	Design modular, microservice-aware system architecture
project-planner	Project Manager	Plan phases, milestones, and dependencies
issue-estimator	Engineering Lead	Break down into 1-2 day sprint-ready issues

Workflow

Execute the following pipeline. Each stage produces artifacts that feed into the next. Do not skip stages. Ask the user for approval at each gate before moving to the next stage.

Stage 1: Kickoff

Read the user's input: $ARGUMENTS
If the description is too vague to start, ask the user clarifying questions about:
- What problem they're solving
- Who the target users are
- Any known constraints (tech stack, timeline, team size)
Determine the initial scope and constraints for the PRD
Create a team using TeamCreate named dev-plan

Stage 2: PRD

Create tasks for the prd-writer agent using TaskCreate:
- Gather requirements from the user via clarifying questions
- Define the problem, target users, and success metrics
- Write the PRD with prioritized requirements (P0/P1/P2)
Spawn the prd-writer agent via Task tool with team_name: "dev-plan" and subagent_type: "dev-team:prd-writer"
- Assign the prd-writer its tasks via TaskUpdate
- The prd-writer should write the PRD to plan/prd.md (or ask user for preferred location)
Gate: PRD Review — When complete, present the PRD summary to the user and ask:
- "Does this PRD capture your requirements? Any changes needed?"
- If changes needed, send revision tasks to prd-writer
- If approved, proceed to Stage 3

Read the full file on GitHub · 146 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.

2d ago First seen · 146 lines · 48 tokens per session scan A 5b986f6d31f7

Subscribe to this mod's changes

dev-plan is a skill published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,811 once invoked, about $0.0002 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.

LLM Planning Project management ai-agents claude-code plugins skills

gh-issues

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…

SafeAI-Lab-X/ClawKeeper · 116 tokens

github

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…

SafeAI-Lab-X/ClawKeeper · 101 tokens

scrum

Scrum framework fundamentals, sprint goal writing, and agile ceremony facilitation. Use when the user asks to plan a sprint, write sprint goals, facilitate daily scrums, run sprint reviews or retrospectives, define scrum roles, manage the product backlog, or apply agile estimation techniques. Covers the three pillars…

krzysztofsurdy/code-virtuoso · 90 tokens

survey

プロジェクト文脈を把握し .claude/context.md を作成する．新しいプロジェクトを始めるときに使う．context.md が既にある場合は /groundwork:theory を使う．.

tomoking2004/claude-plugins · 55 tokens

project-manager

Agent team role for project delivery management using PRINCE2 principles. Use when the user asks to plan project stages, manage risks, track progress, write highlight reports, handle exceptions, create work packages, or ensure continued business justification. Owns the "when" and "how much" — controls stages…

krzysztofsurdy/code-virtuoso · 78 tokens

scrum-master

Agent team role for Scrum Master facilitation, coaching, and servant leadership. Use when the user asks to facilitate scrum events, coach a team on self-management, resolve impediments, run retrospectives, improve team processes, or address scrum anti-patterns. Owns the "how we work" - ensures the team applies scrum…