create-plan

create-plan is a command for coding agents from ihorkatkov/pantheon. It costs 31 tokens per session (3,609 once invoked), scanned A, original, MIT.

An interactive command for turning a task into a detailed implementation plan, meaning a written specification of the work and how it should be carried out.

In plain words
What is it for?
Use it with a task description, ticket, or specification file to review the relevant project documents and develop a thorough technical plan. It does not perform research when no source file is provided.
Why use it?
It helps clarify requirements and uncover missing information before coding starts.

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/ihorkatkov/pantheon/create-plan
Clone the repo
git clone --depth 1 https://github.com/ihorkatkov/pantheon

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/ihorkatkov/pantheon/create-plan.svg)](https://agentmods.dev/commands/ihorkatkov/pantheon/create-plan)
Your own site
<a href="https://agentmods.dev/commands/ihorkatkov/pantheon/create-plan"><img src="https://agentmods.dev/badge/commands/ihorkatkov/pantheon/create-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00031 $0.03609
Opus 5 $0.00015 $0.01804
Sonnet 5 $0.00006 $0.00722
Haiku 4.5 $0.00003 $0.00361

Measured 3d ago against content hash 8f5181da2e95, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] API endpoint returns 200: `curl localhost:<port>/api/new-endpoint`
.opencode/commands/create-plan.md · 487 lines

How it starts

The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Plan

You are tasked with creating detailed implementation plans through an interactive, iterative process. You should be skeptical, thorough, and work collaboratively with the user to produce high-quality technical specifications.

CRITICAL:

  • DO NOT do any research, use file specified from the user. If it's not provided, ask the user to provide it.
  • DO NOT create any timelines or milestones.
  • DO NOT complement choices made by the user: no "Excellent choice", "Great point", or "Very smart", just stick to practical facts and make only relevant observations.

Initial Response

When this command is invoked:

  1. Check if parameters were provided:
  • If a file path or ticket reference was provided as a parameter, skip the default message
  • FIRST: Check if a spec file exists (thoughts/tasks/task-name/spec.md) and read it FULLY
  • Then read the task file and any other provided files FULLY
  • Begin the research process
  1. 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/ticket description (or reference to a ticket file)
2. Link to the spec file if it exists (`thoughts/tasks/task-name/spec.md`)
3. Any relevant context, constraints, or specific requirements
4. Links to related research or previous implementations
5. Use the "guided discovery" method

I'll analyze this information and work with you to create a comprehensive plan.

Tip: You can also invoke this command with a spec or task file directly:
- `/create-plan thoughts/tasks/task-name/spec.md`
- `/create-plan thoughts/tasks/task-name/task.md`

For deeper analysis, try: `/create-plan think deeply about thoughts/tasks/task-name/spec.md`
  1. "guided discovery" method When the "guided discovery" method is selected by the user: Act as a principal engineer using the "guided discovery" method. Your goal is to help me create a robust technical implementation plan.
  • Ask probing, open-ended questions, one at a time.
  • Before every question, you should explore the codebase to do research, and consider doing a web search.
  • Your questions should force me to think critically about all aspects of the plan.

Read the full file on GitHub · 487 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 · 487 lines · 31 tokens per session scan A 8f5181da2e95

Subscribe to this mod's changes

create-plan is a command published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 3,609 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.