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.
npx agentmods add commands/prmichaelsen/gcloud-mcp/acp.proceedgit clone --depth 1 https://github.com/prmichaelsen/gcloud-mcpWrote 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.
[](https://agentmods.dev/commands/prmichaelsen/gcloud-mcp/acp.proceed)<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>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.
| Model | Per session | Once 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 |
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.
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.proceedhas 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-rundetected:
- 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)
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.
- 4d ago First seen · 883 lines · 0 tokens per session scan A aa5426e44555
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.