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/googleads/google-ads-api-developer-assistant/pmax-filtergit clone --depth 1 https://github.com/googleads/google-ads-api-developer-assistantWhat 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 | $0.00014 | $0.00272 |
| Opus 5 | $0.00007 | $0.00136 |
| Sonnet 5 | $0.00003 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
pmax-filter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Performance Max Webpage Filter (/pmax-filter)
Configures Asset Group-level URL expansion exclusions (webpage listing filter trees) for Performance Max campaigns without requiring Page Feeds.
Instructions:
-
Extract Parameters:
- Extract
customer_id,asset_group_id, or URL exclusion rules from$ARGUMENTS. - Resolve API version from
config/api_version.txt.
- Extract
-
Execute Script / Filter Generation:
- Run the listing filter generation script:
python3 skills/pmax-listing-filter/scripts/create_pmax_webpage_filter.py --customer_id "<customer_id>" --asset_group_id "<asset_group_id>" --api_version "<api_version>" - Ensure the filter uses
vertical = WEBPAGEandAssetGroupListingGroupFilterexclusion trees (listing_source = ASSET_GROUP).
- Run the listing filter generation script:
-
Output Format:
- Display generated Python code configured with
GoogleAdsClientandGoogleAdsExceptionhandling. - Remind the user of the NO MUTATE policy: code is saved to
~/saved/code/for review and manual execution.
- Display generated Python code configured with
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.
- 2d ago First seen · 25 lines · 0 tokens per session scan A 737d5abae687
pmax-filter is a command published in the GitHub repository googleads/google-ads-api-developer-assistant (96 stars, last pushed 8d ago), licensed Apache-2.0. It adds 14 tokens to every session and 272 once invoked, about $0.0001 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 commands, from other repositories
feature
Post a feature to the Features Board on production and write tweets.
cluster
Build a complete topic cluster strategy with pillar page definition, 8-12 supporting articles, internal linking map, and creation sequence.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
seo-drift
Compare two SEO snapshots (GSC / GSC AI Performance / rank tracker / AEO probe) and surface top movers per metric with auto-classification — growth / decline / reshuffle / stable / new / lost.