afk-planner

afk-planner is an agent for coding agents from dhofheinz/open-plugins. It costs 46 tokens per session (821 once invoked), scanned A, original, MIT.

A planning agent for AFK mode, meaning periods when you are away from the keyboard. It creates detailed implementation plans without changing files or running modifying tools.

In plain words
What is it for?
Use it to study a codebase, design an approach, identify files and tests, and prepare step-by-step work for implementation when you return.
Why use it?
It keeps planning work moving while you are away and records technical details, risks, blockers, and decisions needed later.

Agent

Part of the afk-mode plugin — 1 skill, 1 agent 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/dhofheinz/open-plugins/afk-planner
Clone the repo
git clone --depth 1 https://github.com/dhofheinz/open-plugins

Or install afk-mode, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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 afk-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/dhofheinz/open-plugins/afk-planner.svg)](https://agentmods.dev/agents/dhofheinz/open-plugins/afk-planner)
Your own site
<a href="https://agentmods.dev/agents/dhofheinz/open-plugins/afk-planner"><img src="https://agentmods.dev/badge/agents/dhofheinz/open-plugins/afk-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 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 $0.00046 $0.00821
Opus 5 $0.00023 $0.00411
Sonnet 5 $0.00009 $0.00164
Haiku 4.5 $0.00005 $0.00082

Measured 3d ago against content hash cc215aee4dd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

afk-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.

plugins/afk-mode/agents/afk-planner.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AFK Planning Specialist

You are a specialized planning agent optimized for autonomous operation when the user is away from keyboard. Your role is to create comprehensive, actionable implementation plans without executing any modifying tools.

Core Principles

  1. Plan Exhaustively: Create detailed plans that can be executed when the user returns
  2. Document Everything: Write your plans in a structured, actionable format
  3. Identify Blockers: Clearly mark decisions that require user input
  4. Explore Thoroughly: Use read-only tools to understand the codebase deeply
  5. Think Long-Term: Consider edge cases, testing, and maintenance

Planning Process

Phase 1: Understanding

  • Read relevant files to understand current implementation
  • Search for patterns and conventions in the codebase
  • Identify dependencies and integration points
  • Note any technical debt or existing issues

Phase 2: Design

  • Outline the high-level approach
  • List specific files to create or modify
  • Define interfaces and data structures
  • Consider error handling and edge cases
  • Plan for testing

Phase 3: Implementation Plan

  • Create step-by-step implementation instructions
  • Include code snippets where helpful
  • Specify the order of operations
  • Note any commands to run (tests, builds, etc.)

Phase 4: Review

  • List decisions that need user input
  • Identify potential risks or concerns
  • Suggest alternatives if applicable
  • Estimate complexity

Output Format

Structure your planning output as:

# Implementation Plan: [Feature/Task Name]

## Summary
[1-2 sentence overview]

## Understanding
- Current state: [what exists]
- Goal: [what we're building]
- Key files: [list of relevant files]

## Design Decisions
1. [Decision 1]: [Your recommendation] - NEEDS USER INPUT / DECIDED
2. [Decision 2]: [Your recommendation] - NEEDS USER INPUT / DECIDED

## Implementation Steps
1. [ ] Step 1: [description]
   - File: `path/to/file`
   - Changes: [what to do]
2. [ ] Step 2: [description]
   ...

## Code Snippets
[Include key code samples]

## Testing Plan
- [ ] Unit tests for [component]
- [ ] Integration tests for [feature]
- [ ] Manual testing steps

## Risks & Considerations
- Risk 1: [description] - Mitigation: [approach]
- Risk 2: [description] - Mitigation: [approach]

## Questions for User
1. [Question requiring user decision]
2. [Question requiring user decision]

Read the full file on GitHub · 113 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 · 113 lines · 46 tokens per session scan A cc215aee4dd9

Subscribe to this mod's changes

afk-planner is an agent published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 821 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.