agentmods.dev

adloop: Command for Claude Code

.claude/commands/budget-plan.md

budget-plan is a command for Claude Code from kLOsk/adloop. It costs 9 tokens per session (330 once invoked), scanned A, original, MIT.

A command for estimating Google Ads keyword budgets using Keyword Planner, Google's tool for forecasting search advertising traffic and costs. It can use keywords, match types, bids, location, language, and an optional daily budget.

In plain words
What is it for?
Forecasting daily advertising results, comparing keyword costs and volume, checking a proposed budget, and choosing keywords or match types when funds are limited.
Why use it?
It helps estimate expected impressions, clicks, cost, and average cost per click before deciding how much to spend. It also shows whether a proposed budget may cover much of the available traffic.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is kLOsk/adloop's own configuration. It tells Claude Code how to work on adloop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adloop configures →

not rated 293repo +2 2d ago A scan 9 tokens original MIT
View source ↗ kLOsk/adloop getadloop.com
Reuse

Borrowing it

Nothing to install: this file belongs to kLOsk/adloop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kLOsk/adloop/main/.claude/commands/budget-plan.md
Clone the repo
git clone --depth 1 https://github.com/kLOsk/adloop

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 budget-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/klosk/adloop/budget-plan/github.svg)](https://agentmods.dev/commands/klosk/adloop/budget-plan)
Your own site
<a href="https://agentmods.dev/commands/klosk/adloop/budget-plan"><img src="https://agentmods.dev/badge/commands/klosk/adloop/budget-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for budget-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/klosk/adloop/budget-plan"><img src="https://agentmods.dev/badge/commands/klosk/adloop/budget-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00009 $0.00330
Opus 5.5 $0.00004 $0.00132
Sonnet 5.5 $0.00002 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 2mo ago against content hash 3e4fe6b88673, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

budget-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 2mo 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.

.claude/commands/budget-plan.md · 35 lines

What it actually says

Plan budget for Google Ads keywords: $ARGUMENTS

1. Gather inputs

  • Target keywords: from user input or suggest based on business context
  • Match types: EXACT or PHRASE preferred (BROAD only with Smart Bidding)
  • Max CPC bids: optional, helps refine forecasts
  • Geography: ask user or infer from existing account (common: 2276=Germany, 2840=USA, 2826=UK)
  • Language: ask user or infer (common: 1000=English, 1001=German, 1002=French)
  • Daily budget: optional — if provided, shows whether it's sufficient

2. Run forecast

  • Call estimate_budget with keywords, match types, optional daily budget, geo target, language
  • The tool uses Google Ads Keyword Planner API (read-only, creates nothing)

3. Present results

  • Estimated daily clicks, impressions, cost, and average CPC
  • If daily budget was provided: is it sufficient to capture most available traffic?
  • Compare estimated CPC across keywords — some may be too expensive
  • Highlight keywords with low forecast volume (may not be worth targeting)

4. Recommendations

  • Suggest a daily budget based on the forecast data
  • If budget is tight, recommend focusing on highest-intent keywords with EXACT match
  • If budget is ample, PHRASE match captures more volume
  • Link to campaign creation: use the forecast to set the budget in draft_campaign
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. 2mo ago First seen · 35 lines · 9 tokens per session scan A 3e4fe6b88673

Subscribe to this mod's changes

budget-plan is a command published in the GitHub repository kLOsk/adloop (293 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 330 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.

Marketing and SEOaicursorga4google-adsgoogle-analyticsmarketing
Related

budget-plan compared with commands from other repositories

budget-plan next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
budget-plankLOsk/adloopCommand2932d agoMITA9Claude Code
seo-auditbsisduck/google-search-ads-analytics-docsCommand25mo agononeA33Claude Code
google-docsbsisduck/google-search-ads-analytics-docsCommand25mo agononeA31Claude Code
setupringo380/ga-mcp-fullCommand027d agoMITA24Claude Code
auth-statusringo380/ga-mcp-fullCommand027d agoMITA16Claude Code
auth-logoutringo380/ga-mcp-fullCommand027d agoMITA15Claude Code
reconnectringo380/ga-mcp-fullCommand027d agoMITB40Claude Code