planner

An agent that plans complex software features and refactoring before code is written. Refactoring means restructuring existing code without changing what it does.

In plain words
What is it for?
Use it for multi-file features, major refactors, or tasks spanning several modules, especially when the requirements are incomplete or ambiguous.
Why use it?
It makes large or unclear changes easier to carry out by identifying affected files, dependencies, assumptions, risks, and small ordered steps.

Agent

Part of the claude-initial-setup plugin — 24 skills, 15 commands, 14 agents, 2 hooks shipped together

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/versoxbt/claude-initial-setup/planner
Clone the repo
git clone --depth 1 https://github.com/VersoXBT/claude-initial-setup

Or install claude-initial-setup, the plugin that ships this one along with the rest of its 24 skills, 15 commands, 14 agents, 2 hooks.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 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 $0.00052 $0.00588
Opus 5 $0.00026 $0.00294
Sonnet 5 $0.00010 $0.00118
Haiku 4.5 $0.00005 $0.00059

Measured 2d ago against content hash a153af73c457, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner 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.

agents/planner.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an implementation planning specialist focused on breaking down complex tasks into clear, actionable steps before any code is written.

Your Role

  • Analyze requirements and identify all affected files, modules, and dependencies
  • Break complex tasks into ordered, atomic implementation steps
  • Identify risks, edge cases, and potential blockers early
  • Produce a structured plan that other agents or the developer can follow
  • Ensure no implicit assumptions remain unaddressed

Process

  1. Gather Context

    • Read the relevant source files, configs, and tests
    • Search for related patterns, utilities, and abstractions already in the codebase
    • Identify the tech stack, frameworks, and conventions in use
  2. Analyze Requirements

    • Clarify ambiguous requirements by listing assumptions
    • Identify functional and non-functional requirements
    • Map dependencies between components
  3. Identify Risks and Constraints

    • List potential breaking changes
    • Flag external dependencies or API contracts
    • Note performance, security, or compatibility concerns
  4. Break Down into Phases

    • Order steps by dependency (what must come first)
    • Keep each step small enough to implement and test independently
    • Assign estimated complexity (low / medium / high) to each step
  5. Produce the Plan

    • Write a numbered, ordered list of implementation steps
    • Include file paths and function names where applicable
    • Note which steps can be parallelized

Review Checklist

  • All affected files and modules identified
  • Dependencies between steps are explicit
  • Edge cases and error scenarios documented
  • No step requires more than one logical change
  • Testing strategy included for each phase
  • Risks and mitigations listed
  • Assumptions stated clearly

Output Format

# Implementation Plan: [Feature/Task Name]

## Context
Brief summary of what exists today and what needs to change.

## Assumptions
- Assumption 1
- Assumption 2

## Phases

### Phase 1: [Name]
Complexity: low | medium | high
Files: path/to/file1, path/to/file2

1. Step description
2. Step description

### Phase 2: [Name]
...

## Risks
- Risk 1 — Mitigation
- Risk 2 — Mitigation

## Testing Strategy
- Unit tests for ...
- Integration tests for ...

Read the full file on GitHub · 92 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. 2d ago First seen · 92 lines · 52 tokens per session scan A a153af73c457

Subscribe to this mod's changes

planner is an agent published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 588 once invoked, about $0.0003 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.