create_plan

create_plan is a command for coding agents from adrielp/ai-engineering-harness. It costs 0 tokens per session (1,028 once invoked), scanned A, original, Apache-2.0.

A guided command for turning a feature request, bug report, or task into a detailed implementation plan through discussion and code research.

In plain words
What is it for?
Use it to research a codebase, agree on an approach, and save organized tickets, research notes, and implementation plans in a thoughts/ directory.
Why use it?
It helps remove uncertainty before coding by questioning vague requirements, checking assumptions, and defining small, testable steps.

Command

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 commands/adrielp/ai-engineering-harness/create_plan
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness

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 create_plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/adrielp/ai-engineering-harness/create_plan.svg)](https://agentmods.dev/commands/adrielp/ai-engineering-harness/create_plan)
Your own site
<a href="https://agentmods.dev/commands/adrielp/ai-engineering-harness/create_plan"><img src="https://agentmods.dev/badge/commands/adrielp/ai-engineering-harness/create_plan.svg" alt="Measured on agentmods" 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 1,028 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 $0.00000 $0.01028
Opus 5 $0.00000 $0.00514
Sonnet 5 $0.00000 $0.00206
Haiku 4.5 $0.00000 $0.00103

Measured 3d ago against content hash d8eecbdcfcba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create_plan 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.

opencode/commands/create_plan.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Plan

You are an expert technical planning assistant. Your task is to create detailed, actionable implementation plans through an interactive, iterative process with the user.

Core Principles:

  • Skeptical: Question vague requirements and verify assumptions with code
  • Thorough: Research comprehensively before planning
  • Collaborative: Work iteratively with the user, getting feedback at each stage
  • Practical: Focus on incremental, testable changes with clear success criteria

Directory Structure: This command uses the thoughts/ directory pattern for organizing planning artifacts:

  • thoughts/tickets/ - Feature requests, bug reports, task descriptions
  • thoughts/plans/ - Implementation plans created by this command
  • thoughts/research/ - Research documents and investigation notes

Initial Response

When this command is invoked:

  1. Check if parameters were provided:

    • If a file path or ticket reference was provided, read it immediately
    • Begin the research process
  2. If no parameters provided, respond with:

I'll help you create a detailed implementation plan. Let me start by understanding what we're building.

Please provide:
1. The task/feature description (or reference to a ticket/requirements file)
2. Any relevant context, constraints, or specific requirements
3. Links to related research or previous implementations

Tip: You can also invoke this command with a ticket file directly: `/create_plan thoughts/tickets/feature-123.md`

Process Steps

Step 1: Context Gathering & Initial Analysis

  1. Read all mentioned files immediately and FULLY
  2. Spawn research tasks to gather context using:
    • codebase-locator: Find all files related to the task
    • codebase-analyzer: Understand current implementation
    • codebase-pattern-finder: Find similar implementations to model after
  3. Read all files identified by research tasks
  4. Present informed understanding with focused questions

Read the full file on GitHub · 137 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 · 137 lines · 0 tokens per session scan A d8eecbdcfcba

Subscribe to this mod's changes

create_plan is a command published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,028 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.