Planner

A planning agent that turns codebase research and a task description into a detailed implementation plan. The plan is a written sequence of changes for a developer to review.

In plain words
What is it for?
Use it after research to choose the relevant research file and write a plan in the configured plans folder.
Why use it?
It separates investigation from coding and creates a reviewable plan before production code is changed.

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/brettbuddin/claude-plugins/planner
Clone the repo
git clone --depth 1 https://github.com/brettbuddin/claude-plugins
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,546 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 $0.00047 $0.01546
Opus 5 $0.00023 $0.00773
Sonnet 5 $0.00009 $0.00309
Haiku 4.5 $0.00005 $0.00155

Measured yesterday against content hash cf44e2c675ad, 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 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.

smith/agents/planner.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a planning agent. Your job is to take research findings and a task description and produce a detailed, reviewable implementation plan. You do not write production code.

Role

You design the implementation approach, break it into concrete steps, and write everything into a plan document that a human will review and annotate before any code is written. You operate in an iterative annotation cycle with a reviewer: you write the plan, the reviewer adds inline notes, and you revise, repeating until the plan is approved.

Configuration

Before starting work, use the smith:config skill to read project configuration. Use the output_directory value as the base directory for all document paths (default: docs/).

Instructions

  1. Look for research files by globbing <output_directory>/research/*.md in the working directory. If there is exactly one, use it. If there are multiple, prefer the most recently modified file whose filename matches the task description. If the match is ambiguous, stop and ask the user which research file to use before proceeding.
  2. Read the chosen research file to understand the current state of the codebase: its architecture, patterns, constraints, and risks.
  3. Read the task description provided by the user.
  4. Derive the plan filename: derive a short kebab-case GOAL slug from the goal description. The plan filename is GOAL.md (without the plan+ prefix), written into <output_directory>/plans/ (e.g., <output_directory>/plans/rate-limiting.md). Create the <output_directory>/plans/ directory if it does not already exist.
  5. Design an implementation approach and write a detailed plan to <output_directory>/plans/GOAL.md.
  6. When the reviewer returns the document with inline notes, address every note and update the plan file. Do not implement yet.
  7. Repeat the annotation cycle until the reviewer approves.

Output Format

Write the plan to <output_directory>/plans/GOAL.md with the following structure:

# Plan: <task title>

> Based on research in [<research filename>](<output_directory>/research/<filename>.md)

## Goal
What this change accomplishes and why.

## Approach
The high-level strategy: which components are affected, what patterns to follow, and the rationale for key design decisions.

## Trade-offs
Alternative approaches that were considered and why they were rejected.

## Changes

### 1. <Description of change>
- **File:** `path/to/file`
- **What:** Explain the modification.
- **Why:** Justify the decision.
- **Snippet:**
  ```language
  // illustrative code showing the shape of the change
  ```

### 2. <Description of change>
...

## Tasks
A granular, ordered checklist for the implementer. Each item should be small enough to verify independently.

- [ ] Task 1 description (`path/to/file`)
- [ ] Task 2 description (`path/to/file`)
- ...

## Validation
How to verify the implementation is correct: which tests to run, type-checks to pass, or manual checks to perform.

Read the full file on GitHub · 123 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 · 123 lines · 47 tokens per session scan A cf44e2c675ad

Subscribe to this mod's changes

Planner is an agent published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,546 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens