plan

A planning command for defining a whole project or writing a feature requirements document. An FRD is a written description of what a feature must do.

In plain words
What is it for?
Use it with no arguments for project planning, or with a feature name or description to create a feature plan and maintain a task list.
Why use it?
It turns a vague project or feature idea into tracked requirements before implementation begins.

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/joncik91/ucai/plan
Clone the repo
git clone --depth 1 https://github.com/Joncik91/ucai
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,721 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 $0.00014 $0.06721
Opus 5 $0.00007 $0.03361
Sonnet 5 $0.00003 $0.01344
Haiku 4.5 $0.00001 $0.00672

Measured 2d ago against content hash a51f63927ab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

commands/plan.md · 650 lines

How it starts

The opening of the file, as written. The whole thing — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planning

You are helping a developer plan before building. This command works at two levels:

  • No arguments (/plan): Define the project — vision, goals, and full requirements backlog
  • With arguments (/plan <feature>): Create a feature FRD grounded in the project spec

Core Principles

  • Spec-driven: Every piece of work traces back to a specification
  • Research before requirements: Understand the codebase and domain first
  • Parallel discovery: Launch multiple agents simultaneously for speed
  • Approval before output: Never write files without user sign-off
  • Track progress: Write and update tasks/todo.md to track phase completion

Skill Loading — MANDATORY

Before starting discovery phases, you MUST identify and load relevant skills. This is not optional.

  1. Always load Skill(ucai:architect) — planning is architecture work
  2. For feature-level planning, also load the domain skill: Skill(ucai:backend), Skill(ucai:frontend), etc.
  3. Apply the skill's guidance throughout all subsequent phases

You MUST load at least one skill before proceeding. State which skill(s) you loaded and why.


Phase 0: Route

Goal: Determine planning level.

Input: $ARGUMENTS

Decision:

  • If $ARGUMENTS is empty or whitespace → Project-Level Mode (Phases 1P–5P)
  • If $ARGUMENTS has content → Feature-Level Mode (Phases 1F–5F)

Project-Level Mode

Use this mode when starting a new project or defining project scope for the first time.

Phase 1P: Understand the Project

Goal: Know what needs to be built.

Actions:

  1. Create todo list with all project-level phases (1P–6P)
  2. If .claude/project.md already exists, read it and ask: "A project spec already exists. Overwrite, refine, or abort?" Wait for user decision.
  3. If .claude/requirements.md already exists, note this — it will be regenerated alongside the project spec.
  4. Determine if this is greenfield (no source code) or brownfield (existing codebase):
    • Use Glob to check for source files: **/*.{js,ts,jsx,tsx,py,go,rs,java,rb,php,cs,cpp,c,swift,kt}
  5. Ask the user:
    • What are you building? (brief description)
    • What problem does it solve? Who is the target user?
    • Any known constraints? (tech stack preferences, deployment target, timeline)
  6. Classify project scale — this calibrates build order (Phase 5P) and milestone scoping (Phase 3F.5):

Read the full file on GitHub · 650 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. 2d ago First seen · 650 lines · 14 tokens per session scan A a51f63927ab9

Subscribe to this mod's changes

plan is a command published in the GitHub repository Joncik91/ucai (29 stars, last pushed 7d ago), licensed MIT. It adds 14 tokens to every session and 6,721 once invoked, about $0.0001 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 2026-08-30.