execute-changes

A command for applying pending changes from a file to a live Google Ads account.

In plain words
What is it for?
Use it to inspect the pending operations and budget impact, then execute them only after the user explicitly confirms.
Why use it?
It adds a review and confirmation step before changes affect the live account, reducing the risk of accidental updates.

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/trueclicks/claude-plugins/execute-changes
Clone the repo
git clone --depth 1 https://github.com/TrueClicks/claude-plugins
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 518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00518
Opus 5 $0.00000 $0.00259
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured yesterday against content hash e56cdaeb164b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-changes scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

mkdir -p tmp && curl -s --max-time 230 -D tmp/response_headers.txt -X POST "https://api.claudeppc.ai/api/cli/google-ads/execute-changes?pluginVersion=1.8.0" -F "[email protected]" -F "pendingChanges=@pending_changes.js
plugins/google-ads/commands/execute-changes.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute Pending Google Ads Changes

Executes the pending changes in pending_changes.json in the live Google Ads account.

IMPORTANT: User Confirmation Required

Before running the execution, you MUST ask the user for confirmation using the AskUserQuestion tool:

Ask the user:

  • Question: "This will apply all pending changes to your live Google Ads account. Are you sure you want to execute these changes?"
  • Header: "Confirm"
  • Options:
    • "Yes, execute changes" — Proceed with execution
    • "No, cancel" — Abort the operation

Only proceed if the user explicitly confirms. If the user selects "No" or any other option, abort and do not run the command.

Execution Steps

  1. Read pending_changes.json and display a summary to the user:

    • Total number of operations
    • Breakdown by operation type
    • Estimated budget impact (if applicable)
  2. ASK FOR USER CONFIRMATION (as described above).

    • If user does not confirm, abort immediately.
  3. If user confirms, POST both files to the API (set Bash timeout to 240000ms — the server may take up to 230 seconds):

mkdir -p tmp && curl -s --max-time 230 -D tmp/response_headers.txt -X POST "https://api.claudeppc.ai/api/cli/google-ads/execute-changes?pluginVersion=1.8.0" -F "[email protected]" -F "pendingChanges=@pending_changes.json"

Check tmp/response_headers.txt for a line starting with X-Plugin-Update:. If found, display its value to the user as a notice. Then delete the headers file: rm -f tmp/response_headers.txt.

  1. If the API call succeeded, archive the results:

    • Create change-history/ directory if it doesn't exist
    • Save pending_changes.json with added status, executed_at, and execution_results fields to change-history/changes-{YYYYMMDD-HHmm}.json
    • Delete pending_changes.json
  2. After the API responds:

    • If successful: summarize what was applied, note the change history file path, and recommend running /google-ads:get to refresh local data.
    • If partially failed: explain which operations succeeded and which failed, and suggest next steps.
    • If completely failed: show the errors and suggest fixes.

Read the full file on GitHub · 45 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. yesterday First seen · 45 lines · 0 tokens per session scan A e56cdaeb164b

Subscribe to this mod's changes

execute-changes is a command published in the GitHub repository TrueClicks/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 518 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.