gx: Command for Claude Code

.claude/commands/plan.md

plan is a command for Claude Code from joshuaboys/gx. It costs 0 tokens per session (605 once invoked), scanned A, a copy of plan, MIT.

A command that starts or continues a project's APS (Anvil Plan Spec) planning records. APS is a file-based way to organize plans, modules, decisions, and work items.

In plain words
What is it for?
Use it to inspect planning files, set up the APS folder structure, report existing modules and work items, and guide the start of a new project plan.
Why use it?
It helps an agent understand the project's existing plans before suggesting or starting work. It also creates the basic planning files when they are missing.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is joshuaboys/gx's own configuration. It tells Claude Code how to work on gx itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joshuaboys/gx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joshuaboys/gx/main/.claude/commands/plan.md
Clone the repo
git clone --depth 1 https://github.com/joshuaboys/gx

Made for: Claude Code.

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 plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/joshuaboys/gx/plan.svg)](https://agentmods.dev/commands/joshuaboys/gx/plan)
Your own site
<a href="https://agentmods.dev/commands/joshuaboys/gx/plan"><img src="https://agentmods.dev/badge/commands/joshuaboys/gx/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 605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 5.1 $0.00000 $0.00605
Opus 5 $0.00000 $0.00302
Sonnet 5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00060

Measured 7d ago against content hash ac8dfa209419, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

Origin

This is a copy

100% identical to plan — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/plan.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan

Start or continue APS planning for this project.

Instructions

You are starting an APS (Anvil Plan Spec) planning session. Follow these steps:

Step 1: Assess current state

Check what APS artefacts already exist:

  1. Look for plans/ directory
  2. Read plans/aps-rules.md if it exists (agent guidance)
  3. Read plans/index.aps.md if it exists (current plan)
  4. Check plans/modules/ for existing module specs
  5. Check for any work items with Ready or In Progress status

Step 2: Bootstrap if needed

If no plans/ directory exists, scaffold the APS structure before continuing:

  1. Check if scaffold/init.sh exists in this repo — if so, run it: bash scaffold/init.sh .
  2. Otherwise, create the structure manually:
    • mkdir -p plans/modules plans/execution plans/decisions
    • Create plans/index.aps.md with an Index template
    • Create plans/aps-rules.md with agent guidance
  3. Tell the user what was created and ask what they're building

If hooks aren't installed, suggest: ./aps-planning/scripts/install-hooks.sh

Step 3: Report what you found

Tell the user:

  • Whether APS is already set up in this project
  • What plans/modules exist and their current status
  • What work items are in progress or ready
  • What the logical next step is

Step 4: Help plan

Based on what the user needs:

If plans exist but are empty: Ask what they're building and help create the right spec. Use the template picker:

Situation Template
Quick feature (1-3 items) Simple spec
Module with boundaries Module spec
Multi-module initiative Index + Modules

If plans exist but need work items: Help define work items with Intent, Expected Outcome, and Validation fields.

If work items are Ready: Ask which to start executing. Create an Action Plan if the work item is complex.

If work items are In Progress: Pick up where the last session left off. Re-read the work item and continue.

Step 5: Create or update files

Read the full file on GitHub · 82 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. 7d ago First seen · 82 lines · 0 tokens per session scan A ac8dfa209419

Subscribe to this mod's changes

plan is a command published in the GitHub repository joshuaboys/gx (10 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 605 tokens. A static security scan graded it A with 0 findings. It is 100% identical to plan, differing in 10 lines, and is treated as a copy.