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 skills/adkit/ads-mcp/analyzenpx skills add adkit/ads-mcp --skill analyzegit clone --depth 1 https://github.com/adkit/ads-mcpWhat 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 | $0.00080 | $0.00745 |
| Opus 5 | $0.00040 | $0.00373 |
| Sonnet 5 | $0.00016 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
analyze 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 3d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Performance
Requires a connected platform — run /ads:setup first if needed.
1. Fetch results
Use adkit_manage with entity: "results" and action: "list" on any connected platform:
adkit_manage platform: "<platform>" entity: "results" action: "list" params: { level: "campaigns", period: "30d" }
Common params (all platforms)
| Param | Description |
|---|---|
level |
campaigns, adsets/ad-groups, ads (Meta also: no level = account; Google also: keywords) |
period |
today, yesterday, 7d, 14d, 30d, this_month, last_month, this_quarter, last_year, maximum |
from / to |
YYYY-MM-DD custom date range (use instead of period) |
sort |
cost, clicks, impressions, conversions |
limit |
Max rows to return |
Use period for presets, or from + to for custom ranges. Don't combine both.
Platform-specific features
Available breakdowns, metrics, and additional actions vary by platform. Call adkit_help path: "manage <platform> results" for the full list. Key differences:
- Meta:
breakdown(day, age, gender, country, device),attribution-window,actionsfilter - Google:
breakdown(device, network), plus separatesearch-terms,placements, andkeywordsactions - TikTok:
dimensionsandmetricspass through to TikTok reporting API
Filtering by entity
Filter results to a specific campaign or ad group:
| Platform | Param |
|---|---|
| Meta | campaign: "<id>", adset: "<id>", ad: "<id>" |
campaignId: "<id>", adGroupId: "<id>" |
|
| TikTok | Uses dimensions — check adkit_help |
2. Google-specific entities
Google Ads has additional entities beyond standard results:
| Entity | Action | Use case |
|---|---|---|
results |
search-terms |
Actual queries that triggered ads |
results |
placements |
Where ads appeared (Display/YouTube) |
keywords |
list |
Managed keyword list for an ad group |
keywords |
create |
Add keywords (including negative match types) |
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.
- 3d ago First seen · 70 lines · 80 tokens per session scan A 6d7c43a653e1
analyze is a skill published in the GitHub repository adkit/ads-mcp (12 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 745 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.
Other skills, from other repositories
hypd-overview
What the HYPD plugin can do — platforms, analyses and slash commands. Use when the user asks what HYPD is, what it can do, or which command fits their task.
hypd-getting-started
Connect HYPD and your ad accounts. Use when HYPD is not connected yet, a HYPD tool returns an authentication error, or the user asks how to set up or start using HYPD.
hypd-tools
How HYPD's tools work and the invariants to respect when calling them. Load before the first HYPD tool call in a session.
dcf-model
Build discounted cash flow valuation workbooks in Excel.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).