ads-optimize

ads-optimize is a skill for Claude Code from AgriciDaniel/claude-ads. It costs 71 tokens per session (363 once invoked), scanned A, original, MIT.

An evidence-based workflow for deciding and preparing changes to paid-ad campaigns. It compares leaving things unchanged, running an experiment, or making a controlled adjustment.

In plain words
What is it for?
Use it to diagnose campaign performance, rank optimization recommendations, reallocate budgets, change bids, pause or archive ads, and review search terms or negative keywords.
Why use it?
It reduces the risk of changing budgets, bids, ads, or keywords based on one misleading metric or without considering tracking, learning, policy, and business effects.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-ads plugin — 30 skills, 25 agents shipped together

Good fit Use it to diagnose campaign performance, rank optimization recommendations, reallocate budgets, change bids, pause or archive ads, and review search terms or negative keywords.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agricidaniel/claude-ads/ads-optimize
About the project

Claude Ads is a Claude Code skill for managing paid-media operations across 12 advertising platforms, using account data or exports to produce audits, plans, creative workflows, experiments, monitoring, and reports. Agencies, consultants, and in-house performance teams use it for source-based analysis and controlled account work. The catalogue entries are its platform-specific skills, workers, and supporting instructions.

AgriciDaniel/claude-ads · 8,921 stars · on GitHub · claude-ads.md

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.

Any agent
npx skills add AgriciDaniel/claude-ads --skill ads-optimize
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/claude-ads

Made for: Claude Code.

Or install claude-ads, the plugin that ships this one along with the rest of its 30 skills, 25 agents.

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 ads-optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/agricidaniel/claude-ads/ads-optimize.svg)](https://agentmods.dev/skills/agricidaniel/claude-ads/ads-optimize)
Your own site
<a href="https://agentmods.dev/skills/agricidaniel/claude-ads/ads-optimize"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-ads/ads-optimize.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 363 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. Third-party audits
  • Socket pass 13 Jul 2026
  • Snyk warn 13 Jul 2026
How audits are shown
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 $0.00071 $0.00363
Opus 5 $0.00036 $0.00181
Sonnet 5 $0.00014 $0.00073
Haiku 4.5 $0.00007 $0.00036

Measured 7d ago against content hash 0f8548e97be9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ads-optimize 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 7d 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.

skills/ads-optimize/SKILL.md · 35 lines

What it actually says

Default to --draft.

  1. Load the latest normalized snapshot, prior decisions, monitoring results, experiment state, conversion lag, economics, and platform capability manifest.
  2. Identify the decision and causal evidence; do not optimize a metric in isolation.
  3. Compare no-change, experiment, and mutation options, including learning, policy, tracking, inventory, and opportunity-cost effects.
  4. Produce ranked recommendations with confidence and success measures.
  5. Convert approved recommendations into mutation plans only through the main mutation gate.
  6. Apply, verify, audit, and retain rollback only when the exact operation is enabled and remote state still matches the draft precondition.

Never use a fixed CPA multiple, budget ratio, benchmark, or novelty claim as sole authorization to change an account.

Destructive-action boundary

Refuse permanent deletion of campaigns, ad groups, ads, audiences, conversions, or other account objects. Permanent deletion is outside the supported mutation contract and cannot be made safe by confirmation. Offer reversible alternatives: leave objects paused, archive where supported, apply labels, export a backup, and define a retention or later-review date. Do not create or apply a delete plan.

Search-term actions require a search terms report, business-relevance evidence, and an overblocking review. Without them, request the missing evidence and do not invent or illustrate specific negative keywords.

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. 7d ago First seen · 35 lines · 71 tokens per session scan A 0f8548e97be9

Subscribe to this mod's changes

ads-optimize is a skill published in the GitHub repository AgriciDaniel/claude-ads (8,921 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 363 once invoked, about $0.0004 per session on Opus 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.

Related

Other skills, from other repositories

email-plan

Generate comprehensive email marketing strategy with 90-day implementation roadmap. Analyzes business type (local-business, saas, ecommerce, creator, agency) to deliver industry-specific segmentation plans, automation sequences, content calendars, KPI targets, platform recommendations, and week-by-week rollout…

AgriciDaniel/claude-email · 71 tokens

email-review

Pre-send email quality review and scoring across 5 dimensions (subject line, copy quality, technical/HTML, deliverability, compliance). Analyzes subject lines, body copy, HTML structure, spam triggers, and CAN-SPAM compliance. Scores 0-100 with detailed recommendations for improvement. Use when user wants to review an…

AgriciDaniel/claude-email · 84 tokens

email-audit

Audits email domain deliverability setup (SPF, DKIM, DMARC, MX records, blacklists, TLS) and generates health score (0-100) with prioritized fix list. Checks bulk sender compliance against Google/Yahoo/Microsoft 2024-2026 requirements. Provides DNS records to add/update. Use when user asks to audit, check, or analyze…

AgriciDaniel/claude-email · 90 tokens

email-check

Intelligent inbox triage that connects to Gmail or Outlook, scores emails by importance (0-100) using sender recognition, urgency keywords, thread depth, time sensitivity, and business relevance, categorizes into Urgent/Important/Routine/Archive, and generates reply suggestions for top priority items. Use when the…

AgriciDaniel/claude-email · 109 tokens

email-sequence

Designs complete email automation sequences with timing, subject lines, copy, and conditional logic. Supports welcome series, nurture campaigns, re-engagement, abandoned cart, post-purchase, review requests, and custom sequences. Adapts sequence type, cadence, frameworks, and conditional branching to business context.…

AgriciDaniel/claude-email · 82 tokens

email-write

Compose high-converting emails using proven copy frameworks (PAS, AIDA, BAB, FAB, 4Ps). Generates subject line variants with scores, responsive HTML templates with dark mode support, plain-text fallback, and preheader recommendations. Optimized for cold outreach, newsletters, product launches, promotions, and…

AgriciDaniel/claude-email · 78 tokens