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 TrueClicks/claude-plugins --skill skill-119-auto-applied-recommendations-reviewgit clone --depth 1 https://github.com/TrueClicks/claude-pluginsWrote 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/trueclicks/claude-plugins/skill-119-auto-applied-recommendations-review)<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-119-auto-applied-recommendations-review"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-119-auto-applied-recommendations-review/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.
<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-119-auto-applied-recommendations-review"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-119-auto-applied-recommendations-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.00641 |
| Opus 5.5 | $0.00010 | $0.00256 |
| Sonnet 5.5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
skill-119-auto-applied-recommendations-review 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 21d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 119: Auto-Applied Recommendations Review
Purpose
Audit and manage Google's auto-applied recommendations to prevent unwanted changes and maintain account control. Unreviewed auto-apply can add irrelevant keywords, change bidding, or expand targeting.
Data Requirements
Data Source: Custom GAQL Required
GAQL Query - Change History:
SELECT
change_event.change_date_time,
change_event.change_resource_type,
change_event.change_resource_name,
change_event.client_type,
change_event.user_email,
change_event.resource_change_operation,
change_event.client_type
FROM change_event
WHERE change_event.change_date_time DURING LAST_14_DAYS
AND change_event.client_type IN ('GOOGLE_ADS_RECOMMENDATIONS', 'GOOGLE_ADS_RECOMMENDATIONS_SUBSCRIPTION')
LIMIT 100
GAQL Query - Pending Recommendations:
SELECT
recommendation.type,
recommendation.campaign
FROM recommendation
Run via /google-ads:get-custom with query name auto_apply_audit.
Analysis Steps
- Identify Auto-Applied Changes: Filter for
GOOGLE_ADS_RECOMMENDATIONS_SUBSCRIPTION(auto-applied) vsGOOGLE_ADS_RECOMMENDATIONS(manually accepted) - Categorize by Risk Level: High-risk (keywords, bidding, targeting) vs. low-risk
- Audit Recent Changes: Review what was auto-applied in last 14 days
- Check Current Settings: Identify which auto-apply types are enabled
Thresholds
| Condition | Severity |
|---|---|
| High-risk auto-apply enabled (keywords, bidding) | Critical |
| >10 auto-applied changes in 30 days | Warning |
| Auto-applied keyword additions | Warning |
| Auto-applied bidding strategy changes | Critical |
Output
Short (default):
## Auto-Applied Recommendations Audit
**Account:** [name] | **Auto-Applied (30d):** [count] | **High-Risk Enabled:** [Yes/No]
### Critical - Disable Immediately
- **Add keywords** - Auto-apply enabled
- **Upgrade to Smart Bidding** - Auto-apply enabled
### Recent Auto-Applied Changes
| Date | Type | Entity | Review |
|------|------|--------|--------|
| [date] | [type] | [entity] | [Revert?] |
### Recommendations
1. Disable high-risk auto-apply: keywords, bidding, targeting expansion
2. Review and revert [count] recent changes
3. Set up weekly change history monitoring
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.
- 21d ago First seen · 83 lines · 24 tokens per session scan A 592525c21811
skill-119-auto-applied-recommendations-review is a skill published in the GitHub repository TrueClicks/claude-plugins (2 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 641 once invoked, about $0.0001 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 2026-10-08.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…