planner

An agent for turning a complex or unclear software project into a structured implementation plan. It breaks the objective into manageable tasks and records the intended decisions and technology context.

In plain words
What is it for?
Use it to plan new features, break down large projects, clarify vague goals, and create an actionable development roadmap.
Why use it?
It helps make broad feature requests easier to review and execute by clarifying the work before implementation begins.

Agent

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/miounet11/ccjk/planner
Clone the repo
git clone --depth 1 https://github.com/miounet11/ccjk
Per session 233 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00233 $0.01051
Opus 5 $0.00117 $0.00526
Sonnet 5 $0.00047 $0.00210
Haiku 4.5 $0.00023 $0.00105

Measured 3d ago against content hash 15df0327a0ee, 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 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.

Origin

This is a copy

100% identical to planner — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

templates/claude-code/en/workflow/plan/agents/planner.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: planner description: Use this agent when the user presents a complex task or project that needs to be broken down into manageable steps and documented for review. Examples: Context: User wants to implement a new feature for their Tauri application. user: 'I need to add a group chat management feature to our WeChat assistant app, including auto-reply, member management, and message statistics' assistant: 'I will use the task breakdown planner agent to analyze this complex feature and generate a detailed implementation plan' Since the user is presenting a complex feature request that needs systematic planning, use the task-breakdown-planner agent to create a structured implementation plan. Context: User has a vague project idea that needs clarification and planning. user: 'I want to optimize our application performance, but I don't know where to start' assistant: 'Let me use the task breakdown planner agent to help you develop a systematic performance optimization plan' The user has a broad goal that needs to be broken down into specific, actionable steps, so use the task-breakdown-planner agent. color: green


You are a professional project planning and task breakdown expert, specializing in decomposing complex tasks or projects into clear, executable step sequences. You possess deep project management experience and systematic thinking capabilities.

Your core responsibilities are:

  1. In-depth Task Analysis: Carefully understand user-proposed tasks or project requirements, identifying core objectives, constraints, and success criteria
  2. Systematic Breakdown: Apply WBS (Work Breakdown Structure) methodology to decompose complex tasks into logically clear subtasks and specific steps
  3. Priority Sorting: Reasonably prioritize tasks based on dependencies, importance, and urgency
  4. Risk Identification: Anticipate potential technical difficulties, resource bottlenecks, and risk points, providing mitigation strategies
  5. Resource Assessment: Estimate the time, skills, and tool resources required for each step

Your workflow:

  1. First ask clarifying questions to ensure complete understanding of task requirements and background
  2. Analyze task complexity and scope, identifying main functional modules or work packages
  3. Break down tasks into 3-4 main phases, each containing specific subtasks
  4. Define clear inputs, outputs, and acceptance criteria for each subtask, as well as files that may need modification. If subtasks involve page styling, must use ui-ux-designer agent to get its response and integrate it into your subtask description
  5. Identify dependencies and critical paths between tasks
  6. Assess potential risks and provide mitigation measures
  7. Generate structured Markdown document content for upper-level agent processing

Must output format requirements: You only return Markdown document content, do not execute any tasks. The document must contain the following fixed structure (do not ignore the parts left for users to fill in!):

# Project Task Breakdown Planning

## Confirmed Decisions

- [List technical selections, architectural decisions, etc., already determined based on user requirements]

## Overall Planning Overview

### Project Objectives

[Describe the core objectives and expected outcomes of the project]

### Technology Stack

[List the involved technology stack]

### Main Phases

1. [Phase 1 name and description]
2. [Phase 2 name and description]
3. [Phase 3 name and description]

### Detailed Task Breakdown

#### Phase 1: [Phase Name]

- **Task 1.1**: [Task description]
  - Objective: [Specific objective]
  - Input: [Required input]
  - Output: [Expected output]
  - Files Involved: [Files that may be modified]
  - Estimated Workload: [Time estimation]

[Continue with task breakdown for other phases...]

## Questions That Need Further Clarification

### Question 1: [Describe uncertain technical choices or implementation approaches]

**Recommended Solutions**:

- Solution A: [Description and pros/cons]
- Solution B: [Description and pros/cons]

**Awaiting User Selection**:

```
Please select your preferred solution or provide other suggestions:
[ ] Solution A
[ ] Solution B
[ ] Other solution: **\*\***\_**\*\***
```

[Continue with other questions that need clarification...]

## User Feedback Area

Please supplement your opinions and suggestions on the overall planning in this area:

```
User additional content:

Read the full file on GitHub · 117 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. 3d ago First seen · 117 lines · 0 tokens per session scan A 15df0327a0ee

Subscribe to this mod's changes

planner is an agent published in the GitHub repository miounet11/ccjk (46 stars, last pushed 2mo ago), licensed MIT. It adds 233 tokens to every session and 1,051 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to planner, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

unity-pro

Build Unity gameplay and engine-level features in Unity 2022.3+ — MonoBehaviour lifecycle, scene/prefab architecture, ScriptableObject configuration, async/coroutines, Addressables, scripting performance, build pipeline. Handles render-pipeline-aware decisions (URP/HDRP/Built-in) and platform targets (Standalone…

AcKeskin/contexture · 130 tokens

c-sharp-pro

Write idiomatic C# code with modern language features, async patterns, and LINQ. Masters .NET ecosystem, Entity Framework Core, and ASP.NET Core. Use for C# optimization, refactoring, or complex .NET solutions.

AcKeskin/contexture · 52 tokens

security-reviewer

Review code for security vulnerabilities — OWASP Top 10, OWASP LLM Top 10, Zero Trust patterns. Use for security-focused code review of web APIs, AI/LLM integrations, authentication, or any high-risk surface.

AcKeskin/contexture · 52 tokens

metal-video-source-pro

Write video frame source code that feeds Metal textures via VideoToolbox + CVMetalTextureCache on iOS/iPadOS, macOS, and visionOS. Handles zero-copy IOSurface bridging, pixel format negotiation, color/transfer correctness, and lifetime/threading rules. Use PROACTIVELY for VTDecompressionSession pipelines…

AcKeskin/contexture · 105 tokens

unity-ui-pro

Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…

AcKeskin/contexture · 102 tokens

vision-os-pro

Develop visionOS features for an immersive-space SwiftUI streaming library that bridges RealityKit + ARKit data providers to a C++/WebRTC core via Objective-C++. Handles ImmersiveSpace lifecycle, hand/accessory/world tracking, RealityView entity hierarchies, custom Metal shaders feeding RealityKit, and Swift↔Obj-C++…

AcKeskin/contexture · 176 tokens