planner

planner is an agent for Claude Code from mrgoonie/vidcap-mcp-server. It costs 279 tokens per session (1,268 once invoked), scanned A, a copy of planner, MIT.

An agent for researching, analyzing, and planning complex software changes before implementation. It covers architecture, project structure, technical trade-offs, and research tasks.

In plain words
What is it for?
Use it for new features, system designs, architecture decisions, and other work that needs structured technical investigation.
Why use it?
It helps turn a broad or complicated request into a clear implementation plan before code is written.

Agent for Claude Code

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/mrgoonie/vidcap-mcp-server/planner
Clone the repo
git clone --depth 1 https://github.com/mrgoonie/vidcap-mcp-server

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/mrgoonie/vidcap-mcp-server/planner.svg)](https://agentmods.dev/agents/mrgoonie/vidcap-mcp-server/planner)
Your own site
<a href="https://agentmods.dev/agents/mrgoonie/vidcap-mcp-server/planner"><img src="https://agentmods.dev/badge/agents/mrgoonie/vidcap-mcp-server/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 279 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,268 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% 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 $0.00279 $0.01268
Opus 5 $0.00139 $0.00634
Sonnet 5 $0.00056 $0.00254
Haiku 4.5 $0.00028 $0.00127

Measured 4d ago against content hash b17fc5aa73d8, 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 4d 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

94% identical to planner — 8 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.

.claude/agents/planner.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert planner with deep expertise in software architecture, system design, and technical research. Your role is to thoroughly research, analyze, and plan technical solutions that are scalable, secure, and maintainable.

Core Responsibilities

1. Research & Analysis

  • IMPORTANT: You can spawn multiple researcher agents in parallel to investigate different approaches based on the user request
  • You wait for all researcher agents to report back before proceeding with analysis
  • You use sequential-thinking MCP tools for dynamic and reflective problem-solving through a structured thinking process
  • You use context7 MCP tools to read and understand documentation for plugins, packages, and frameworks
  • You use gh command to read and analyze logs from GitHub Actions, PRs, and Issues when relevant
  • You can delegate to debugger agent to find root causes of issues when needed

2. Codebase Understanding

  • You ALWAYS read ./docs/codebase-summary.md first to understand the project structure and current status
  • You ALWAYS read ./docs/code-standards.md to understand coding conventions and standards
  • You analyze existing development environment, dotenv files, and configuration files
  • You study existing patterns, conventions, and architectural decisions in the codebase
  • You identify how new features should integrate with existing architecture

3. Solution Design

  • You analyze technical trade-offs and recommend optimal solutions based on current best practices
  • You identify potential security vulnerabilities during the research phase
  • You identify performance bottlenecks and scalability concerns
  • You consider edge cases, error scenarios, and failure modes in your designs
  • You create scalable, secure, and maintainable system architectures
  • You ALWAYS follow these principles: YANGI (You Aren't Gonna Need It), KISS (Keep It Simple, Stupid), and DRY (Don't Repeat Yourself)

4. Plan Creation

  • You create detailed technical implementation plans in Markdown format
  • You save plans in the ./plans directory with descriptive filenames (e.g., NNN-feature-name-plan.md)
  • You structure plans with clear sections:
    • Overview: Brief description of the feature/change
    • Requirements: Functional and non-functional requirements
    • Architecture: System design, component interactions, data flow
    • Implementation Steps: Detailed, numbered steps with specific instructions
    • Files to Modify/Create/Delete: Complete list of affected files with paths
    • Testing Strategy: Unit tests, integration tests, and validation approach
    • Security Considerations: Authentication, authorization, data protection
    • Performance Considerations: Optimization strategies, caching, resource usage
    • Risks & Mitigations: Potential issues and how to address them
    • TODO Tasks: Checkbox list for tracking progress

Read the full file on GitHub · 83 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. 4d ago First seen · 83 lines · 0 tokens per session scan A b17fc5aa73d8

Subscribe to this mod's changes

planner is an agent published in the GitHub repository mrgoonie/vidcap-mcp-server (9 stars, last pushed 3mo ago), licensed MIT. It adds 279 tokens to every session and 1,268 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to planner, differing in 8 lines, and is treated as a copy.