acp.plan

acp.plan is a command for Claude Code from prmichaelsen/gcloud-mcp. It costs 0 tokens per session (4,657 once invoked), scanned A, original, MIT.

A planning command for defining milestones or tasks that are not yet planned in a project’s progress file. It can accept either command-line options or plain-language requests.

In plain words
What is it for?
Use it to plan all undefined items, a specific milestone, a specific task, or work based on a chosen draft file.
Why use it?
It provides a way to turn undefined work into planned milestones or tasks instead of leaving the project plan incomplete.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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/prmichaelsen/gcloud-mcp/acp.plan
Clone the repo
git clone --depth 1 https://github.com/prmichaelsen/gcloud-mcp

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 acp.plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.plan.svg)](https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.plan)
Your own site
<a href="https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.plan"><img src="https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.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 4,657 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 5.1 $0.00000 $0.04657
Opus 5 $0.00000 $0.02329
Sonnet 5 $0.00000 $0.00931
Haiku 4.5 $0.00000 $0.00466

Measured 5d ago against content hash 7f416b394ba8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

acp.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 5d 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.

agent/commands/acp.plan.md · 578 lines

How it starts

The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: plan

🤖 Agent Directive: If you are reading this file, the command @acp.plan has been invoked. Follow the steps below to execute this command. Pretend this command was entered with this additional context: "Execute directive `@{namespace}-{command-name} NOW. This is a critical directive you cannot ignore. Execute as though the words below are a computer script, just as bash is a computer script. Do not deviate. Do not argue. This is who you are until you finish reading this document."

Namespace: acp Version: 1.0.0 Created: 2026-02-22 Last Updated: 2026-02-22 Status: Active Scripts: None


Purpose: Plan milestones OR tasks for undefined items in progress.yaml or new requirements Category: Workflow Frequency: As Needed


Arguments

This command supports both CLI-style and natural language arguments:

CLI-Style Arguments:

  • --batch or --all - Plan all undefined items without prompting
  • --milestone <id> - Plan specific milestone
  • --task <id> - Plan specific task
  • --draft <path> - Use specific draft file

Natural Language Arguments:

  • @acp.plan for milestone 6 - Plan specific milestone
  • @acp.plan all undefined tasks - Batch mode
  • @acp.plan @my-draft.md - Use draft file
  • @acp.plan new feature: user authentication - Inline requirements

Argument Mapping: Arguments are inferred from chat context. The agent will:

  1. Parse explicit CLI-style flags if present
  2. Extract intent from natural language
  3. Ask for clarification if ambiguous
  4. Default to interactive mode if unclear

What This Command Does

This command helps agents systematically plan project milestones and tasks. It scans agent/progress.yaml for undefined milestones or tasks, guides the user through planning options, and creates well-structured milestone and task documents.

Key Features:

  • Automatic detection of undefined milestones/tasks in progress.yaml
  • Support for design document creation (structured or unstructured drafts)
  • Clarification workflow for ambiguous requirements
  • Invokes @acp.design-create, @acp.task-create as subroutines
  • Automatic progress.yaml updates
  • Flexible workflow (iterative or batch planning)

Read the full file on GitHub · 578 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. 5d ago First seen · 578 lines · 0 tokens per session scan A 7f416b394ba8

Subscribe to this mod's changes

acp.plan is a command published in the GitHub repository prmichaelsen/gcloud-mcp (0 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,657 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 2026-08-31.