tommymorgan:plan

A command for turning a feature idea into a structured implementation plan, beginning with brainstorming and Gherkin scenarios. Gherkin is a plain-language format for describing software behavior as given conditions, actions, and expected results.

In plain words
What is it for?
Use it to brainstorm a feature, identify the relevant project, check its existing technology stack, and produce reviewed requirements and a feature plan.
Why use it?
It helps clarify the feature, project location, and technology choices before detailed technical specifications are written.

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/tommymorgan/claude-plugins/plan
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,468 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 $0.00019 $0.02468
Opus 5 $0.00010 $0.01234
Sonnet 5 $0.00004 $0.00494
Haiku 4.5 $0.00002 $0.00247

Measured 2d ago against content hash 20de723be8b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tommymorgan: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.

tommymorgan/planning/commands/plan.md · 375 lines

How it starts

The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Feature Plan

Create a comprehensive feature plan through collaborative brainstorming, generating Gherkin scenarios with expert review and quality assurance.

Workflow

Step 1: Invoke Brainstorming

Use the Skill tool to invoke the brainstorming skill:

Skill("tommymorgan:brainstorming")

Brainstorm the feature described by the user: $ARGUMENTS

The brainstorming skill handles question strategy, approach exploration, and section-level expert review.

Step 2: Determine Project Location

Infer the project location from context:

  • Current working directory
  • Recently accessed files
  • Conversation context

Projects live in apps/, libs/, or tools/ directories.

If ambiguous, use AskUserQuestion to ask: "Which project does this feature belong to?" Options: List detected projects from apps/, libs/, tools/

Step 3: Technology Checkpoint

After brainstorming completes and before writing Technical Specifications, verify technology decisions with the user.

Scan for existing technology stack:

Read project files to detect technologies already in use:

  • package.json — Node.js runtime, frameworks (React, SolidJS, Express, etc.), build tools (Vite, esbuild), test frameworks (Vitest, Jest)
  • pyproject.toml / requirements.txt — Python version, frameworks (FastAPI, Django, Flask)
  • Cargo.toml — Rust edition, dependencies
  • go.mod — Go version, modules
  • Dockerfiles / docker-compose.yml — Container runtimes, database versions
  • Makefile / justfile — Build tooling
  • .tool-versions / .nvmrc / .python-version — Version managers

Report detected technologies:

I see you're using: [SolidJS, Vite, Vitest, pnpm, TypeScript 5.4]

Identify undecided technology decisions:

Compare what the plan needs against what's already determined. Only ask about decisions that are genuinely open.

Examples of decisions that might be needed:

  • Database choice (if plan requires new data storage)
  • Authentication approach (if plan adds auth)
  • API framework (if plan adds a new service)
  • Testing strategy (if project has no existing test setup)

Read the full file on GitHub · 375 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 · 375 lines · 19 tokens per session scan A 20de723be8b0

Subscribe to this mod's changes

tommymorgan:plan is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,468 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 2026-08-31.