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 adaptyteam/adapty-skills --skill ads-managergit clone --depth 1 https://github.com/adaptyteam/adapty-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/adaptyteam/adapty-skills/ads-manager)<a href="https://agentmods.dev/skills/adaptyteam/adapty-skills/ads-manager"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/ads-manager/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/adaptyteam/adapty-skills/ads-manager"><img src="https://agentmods.dev/badge/skills/adaptyteam/adapty-skills/ads-manager.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 | $0.00117 | $0.07394 |
| Opus 5.5 | $0.00047 | $0.02958 |
| Sonnet 5.5 | $0.00023 | $0.01479 |
| Haiku 4.5 | $0.00012 | $0.00739 |
Grade A, and why
ads-manager 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 13d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Search Ads through the Adapty CLI
Reads and automations run --dry-run cost nothing. Every other asa command reaches Apple
within seconds and spends real money, and nothing it creates can be deleted or undone — except
asa segments, which writes an audience to Adapty and never touches Apple (workflow 13).
Open the reference a workflow names before running its commands:
references/asa-management.md— campaigns, ad groups, ads, keywords and keyword recommendations, negative keywords, product pages, creatives, segments, automations, change history.references/asa-metrics.md—metrics,metrics overview,search-terms list,competitors summary.
How you sound
Every line the user reads:
- "I" for what you do, "you" for what they do. Lead with the answer — the number, the change — and end on one next step. No opener, no recap of their request.
- Bold at most one thing per paragraph. Table rows need no bold.
- Raw values only when the user will type them or see them elsewhere — a campaign, ad group or keyword name as Apple Ads shows it, an amount in its currency, a command they run. Entity UUIDs only inside a command.
- Before a change, name exactly what moves and what does not — the entity, the old and new value — then ask once.
- Full, clickable links. Reply in the user's language; names from Apple Ads stay as Apple Ads shows them.
The CLI
Resolve $ADAPTY once, before your first asa call, and use it for every command you run. A
global adapty is frequently old. The asa topic ships in 0.4.0, but ad-groups create --automated and the five --invoice-* flags ship in 0.8.2, the metrics scope flags and the
automations action flags in 0.8.3, and keywords recommend in 0.8.7, so treat 0.8.7 as this
skill's floor. asa segments ships after 0.9.3 and is the one exception to the floor: probe
$ADAPTY asa segments --help before workflow 13 instead of raising it for everyone. An older install answers with unknown command or an unknown-flag error, which reads
like the command does not exist rather than like a stale CLI:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +63 lines · +37 tokens per session 3c8274d1f6a6
- 21d ago Changed · +15 lines 91e12aee6c50
- 1mo ago Changed · +13 lines · +7 tokens per session 6d11a29d05e1
- 1mo ago Changed · +2 lines a8408a58dacc
- 1mo ago Changed · +4 lines 0f46c904d7b0
- 1mo ago Changed · +17 lines 5ce428269284
- 1mo ago Changed · +39 lines · +15 tokens per session 1edb251fad50
- 1mo ago First seen · 268 lines · 58 tokens per session scan A a19d2d6760f5
ads-manager is a skill published in the GitHub repository adaptyteam/adapty-skills (6 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 7,394 once invoked, about $0.0005 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 2026-08-31.
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…