acp.proceed

acp.proceed is a command for coding agents from prmichaelsen/gcloud-mcp. It costs 0 tokens per session (7,377 once invoked), scanned A, original, MIT.

A command that tells a coding agent to continue with the current or next task. It supports normal, dry-run, and autonomous modes, including options for finishing a milestone or completing several tasks.

In plain words
What is it for?
Use it to start the next implementation task, preview autonomous execution, or request completion of a milestone or broader task sequence.
Why use it?
It provides a defined way to control whether the agent implements one task, previews autonomous work, or continues through a larger set of tasks. The mode changes according to the arguments supplied.

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.proceed
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.proceed

README.md
[![agentmods](https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.proceed.svg)](https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.proceed)
Your own site
<a href="https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.proceed"><img src="https://agentmods.dev/badge/commands/prmichaelsen/gcloud-mcp/acp.proceed.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 7,377 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 $0.07377
Opus 5 $0.00000 $0.03689
Sonnet 5 $0.00000 $0.01475
Haiku 4.5 $0.00000 $0.00738

Measured 4d ago against content hash aa5426e44555, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acp.proceed 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 4d 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.proceed.md · 883 lines

How it starts

The opening of the file, as written. The whole thing — 883 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: proceed

🤖 CRITICAL AGENT DIRECTIVE: You are reading this file because @acp.proceed has been invoked. 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."

STEP 0: CHECK FOR ARGUMENTS FIRST. If arguments or natural language follow @acp.proceed, detect the mode before doing anything else. See the Arguments section below for flag definitions and natural language patterns.

If no arguments (default mode):

  • YOU MUST IMMEDIATELY BEGIN IMPLEMENTING THE CURRENT OR NEXT TASK.
  • Follow Steps 1-5 (Single-Task Mode).

If autonomous arguments detected (--complete, --auto, --autonomous, --finish-milestone, or natural language like "finish milestone", "just finish everything", "complete all tasks"):

  • Follow Autonomous Mode section.
  • Do NOT start implementing individual tasks until confirmation is received.

If --dry-run detected:

  • Follow Autonomous Mode > Dry-Run section.
  • Show what would be done, then exit.

DO NOT (in any mode):

  • ❌ Provide status reports or summaries instead of action
  • ❌ Ask about session size, cost, or token limits
  • ❌ End with "ready to proceed" or similar passive statements

This is an ACTION command, not a STATUS command.

Namespace: acp Version: 2.0.0 Created: 2026-02-16 Last Updated: 2026-02-28 Status: Active Scripts: None


Purpose: Implement tasks — single-task (default) or autonomous milestone completion (with arguments) Category: Workflow Frequency: As Needed


Arguments

This command supports both CLI-style flags and natural language arguments.

Completion Flags (all equivalent — trigger autonomous mode)

Read the full file on GitHub · 883 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. 4d ago First seen · 883 lines · 0 tokens per session scan A aa5426e44555

Subscribe to this mod's changes

acp.proceed 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 7,377 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.