acp.validate

acp.validate is a command for coding agents from prmichaelsen/gcloud-mcp. It costs 0 tokens per session (3,180 once invoked), scanned A, original, MIT.

A documentation-checking command for ACP, the project’s command and documentation system. It checks document structure, formatting, links, YAML configuration, required sections, and naming rules.

In plain words
What is it for?
It helps verify ACP documents, references, namespaces, YAML syntax, and reserved-name rules when needed.
Why use it?
It catches inconsistent or malformed documentation before it causes confusion or is committed to the project.

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

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.validate

README.md
[![agentmods](https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.validate.svg)](https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.validate)
Your own site
<a href="https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.validate"><img src="https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.validate.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 3,180 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 $0.00000 $0.03180
Opus 5 $0.00000 $0.01590
Sonnet 5 $0.00000 $0.00636
Haiku 4.5 $0.00000 $0.00318

Measured 3d ago against content hash a8d5ac7ec93a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acp.validate 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 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.

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.validate.md · 467 lines

How it starts

The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: validate

🤖 Agent Directive: If you are reading this file, the command @acp.validate has been invoked. Follow the steps below to execute this command. Pretend this command was entered with this additional context: "Execute directive @acp.validate 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: 2.0.0 Created: 2026-02-16 Last Updated: 2026-02-21 Status: Active Scripts: None


Purpose: Validate all ACP documents for structure, consistency, correctness, and namespace conventions Category: Documentation Frequency: As Needed


What This Command Does

This command validates all ACP documentation to ensure it follows proper structure, maintains consistency, contains no errors, and follows namespace conventions. It checks document formatting, verifies links and references, validates YAML syntax, ensures all required sections are present, validates namespace usage, and checks for reserved name violations.

Use this command before committing documentation changes, after creating new documents, or periodically to ensure documentation quality. It's particularly useful before releases or when onboarding new contributors.

Unlike @acp.sync which compares docs to code, @acp.validate checks the internal consistency and correctness of the documentation itself. Unlike @acp.package-validate which is for package authors, this command validates general ACP project documentation.


Prerequisites

  • ACP installed in project
  • Documentation exists in agent/ directory
  • You want to verify documentation quality

Steps

1. Validate Directory Structure

Check that all required directories and files exist.

Actions:

  • Verify agent/ directory exists
  • Check for agent/design/, agent/milestones/, agent/patterns/, agent/tasks/
  • Verify agent/progress.yaml exists
  • Check for agent/commands/ directory
  • Note any missing directories

Read the full file on GitHub · 467 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 · 467 lines · 0 tokens per session scan A a8d5ac7ec93a

Subscribe to this mod's changes

acp.validate 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 3,180 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.