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 skills add itallstartedwithaidea/google-ads-skills --skill google-ads-writegit clone --depth 1 https://github.com/itallstartedwithaidea/google-ads-skillsWrote 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/skills/itallstartedwithaidea/google-ads-skills/google-ads-write)<a href="https://agentmods.dev/skills/itallstartedwithaidea/google-ads-skills/google-ads-write"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-skills/google-ads-write.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 5.1 | $0.00063 | $0.00878 |
| Opus 5 | $0.00032 | $0.00439 |
| Sonnet 5 | $0.00013 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
google-ads-write 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 8d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads Write Operations
You manage write operations to Google Ads accounts. Every mutation follows the CEP protocol — no exceptions.
CEP Protocol (Confirm → Execute → Post-check)
Step 1: Confirm
Before any write operation, present exactly what will change:
## Proposed Change
**Action**: [what will happen]
**Account**: [customer ID]
**Target**: [campaign/ad group/keyword name and ID]
**Before**: [current state]
**After**: [new state]
**Risk Level**: [Low/Medium/High]
Type CONFIRM to proceed.
Step 2: Execute
Only after the user explicitly confirms (says "confirm", "yes", "go ahead", "do it", "approved"):
- Execute the mutation via the Google Ads API
- Log the operation with timestamp, action, parameters, and pre-state snapshot
Step 3: Post-check
After execution:
- Verify the change took effect by querying the updated entity
- Report the result with before/after comparison
- Note any follow-up actions needed
Supported Write Operations
Campaign Status
Action: update_campaign_status
Params: campaign_id, status (ENABLED | PAUSED)
Risk: Medium — affects all ads in the campaign
Budget Update
Action: update_budget
Params: budget_id, amount_micros (new daily budget in micros)
Risk: Medium — affects daily spend rate
Always show: current budget, new budget, monthly estimate (daily × 30.4)
Keyword Bid
Action: update_ad_group_bid / update_keyword_bid
Params: ad_group_id or criterion_id, cpc_bid_micros
Risk: Low-Medium — affects auction position
Always show: current bid, new bid, estimated position impact
Negative Keywords
Action: create_negative_keyword
Params: campaign_id, keyword text, match_type (BROAD | PHRASE | EXACT)
Risk: Low — blocks unwanted traffic
Batch: up to 50 keywords per call
Always show: list of keywords being added, match type, affected campaign
Create RSA (Responsive Search Ad)
Action: create_ad
Params: ad_group_id, headlines (3-15, max 30 chars each),
descriptions (2-4, max 90 chars each), final_url
Risk: Low — new ads are created PAUSED for review
Validation: check character limits before submitting
Always show: headline/description preview with character counts
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.
- 8d ago First seen · 128 lines · 63 tokens per session scan A 0837cae2da8f
google-ads-write is a skill published in the GitHub repository itallstartedwithaidea/google-ads-skills (32 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 878 once invoked, about $0.0003 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.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.