planner

planner is an agent for Claude Code from UfoMiao/zcf. It costs 0 tokens per session (1,051 once invoked), scanned A, original, MIT.

An assistant for breaking complex projects into clear, ordered tasks and phases.

In plain words
What is it for?
Use it to plan features or other projects, define work packages, identify risks, and prepare steps for review and execution.
Why use it?
It turns broad requests into a plan that accounts for dependencies, priorities, risks, and needed resources.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to plan features or other projects, define work packages, identify risks, and prepare steps for review and execution.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ufomiao/zcf/planner
About the project

ZCF is a command-line setup tool for configuring Claude Code and Codex with agents, instructions, skills, hooks, commands, and settings. It is for developers who want to install and personalize these coding-agent workflows through an interactive setup.

UfoMiao/zcf · 6,078 stars · on GitHub · zcf.ufomiao.com

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.

Clone the repo
git clone --depth 1 https://github.com/UfoMiao/zcf

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/ufomiao/zcf/planner/github.svg)](https://agentmods.dev/agents/ufomiao/zcf/planner)
Your own site
<a href="https://agentmods.dev/agents/ufomiao/zcf/planner"><img src="https://agentmods.dev/badge/agents/ufomiao/zcf/planner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/ufomiao/zcf/planner"><img src="https://agentmods.dev/badge/agents/ufomiao/zcf/planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 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. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01051
Opus 5.5 $0.00000 $0.00420
Sonnet 5.5 $0.00000 $0.00210
Haiku 4.5 $0.00000 $0.00105

Measured 1mo ago against content hash 15df0327a0ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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

Copies of this mod

1 near-identical copy found in the catalogue:

  • planner — 100% identical, 0 lines differ
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.

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:

---

---

---

```

```

Special Notes:

- Consider the characteristics of the current project's technology stack
- Follow agile development and iterative delivery principles
- Ensure each step is testable and verifiable
- Maintain a pragmatic attitude, avoid overly complex planning
- During planning, pay attention to code reusability, avoid reinventing the wheel
- **You are only responsible for generating planning document content, not executing specific development tasks**
- When encountering uncertain technical implementations or design choices, list them in the "Questions That Need Further Clarification" section and wait for user feedback

Before starting the breakdown, you will proactively ask necessary clarifying questions to ensure the accuracy and practicality of the planning.
```

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. 1mo 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 UfoMiao/zcf (6,078 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,051 tokens. 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.

Related

Other agents, from other repositories

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

code-reviewer

Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.

opencue/cuecards · 35 tokens

scramjet:instruction-semantics-analyzer

Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.

LeanAndMean/scramjet · 35 tokens