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 AppKittie/aso-mcp-skills --skill app-researchgit clone --depth 1 https://github.com/AppKittie/aso-mcp-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/appkittie/aso-mcp-skills/app-research)<a href="https://agentmods.dev/skills/appkittie/aso-mcp-skills/app-research"><img src="https://agentmods.dev/badge/skills/appkittie/aso-mcp-skills/app-research/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/appkittie/aso-mcp-skills/app-research"><img src="https://agentmods.dev/badge/skills/appkittie/aso-mcp-skills/app-research.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 | $0.00054 | $0.00755 |
| Opus 5.5 | $0.00022 | $0.00302 |
| Sonnet 5.5 | $0.00011 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
app-research 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 today.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AppKittie research
Use the AppKittie MCP tools exposed by this plugin. Tool schemas are the source of truth for argument names and supported values. Match the user's requested storefront, platform, time period, and research scope; ask only for missing information that materially changes the result.
Account connection
Protected tools require an AppKittie account connection. Use the host's account linking flow when prompted. Users sign in on AppKittie, choose a team, and approve access. Never ask for passwords, API keys, or access tokens in the conversation. An eligible subscription and API credits are required for paid research tools. An authentication failure means the user should reconnect; a credit or rate-limit error should be explained without repeatedly retrying chargeable requests.
Choose tools
- Discover apps with
search_apps; resolve ambiguous names before comparisons. App-scoped tools accept supported identifiers such as store URLs or app slugs. - Compare metadata and estimated revenue with
get_app_detail. Useget_app_historicalsfor actual series instead of extrapolating from summaries, andget_app_countriesfor where an app's users are. - Use
list_store_rankingsfor a current chart andget_store_ranking_historyfor an app's positions over time. - Research one keyword with
get_keyword_difficulty; usebatch_keyword_difficultyfor a user-requested set of up to ten keywords. - Search ad creatives with
search_ads; expand only relevant items withget_ad_detail. Uselist_creatorsandlist_organic_contentfor creator discovery and evidence of posts about an app. - Use
get_app_reviewsto analyze a bounded sample of store reviews. - Use
search_onboarding_screensfor onboarding design research. - Use
list_favorite_appsfor the connected team's owner's saved apps and folders. Do not describe them as the individual connecting user's collection unless that user is the team owner. - Use
get_supported_countriesfor supported storefront codes; it is public.
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.
- today Changed · +1 lines ad763d5439ad
- 8d ago First seen · 65 lines · 54 tokens per session scan A 3bf849f39e47
app-research is a skill published in the GitHub repository AppKittie/aso-mcp-skills (7 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 755 once invoked, about $0.0002 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 2026-10-29.
app-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| app-researchAppKittie/aso-mcp-skills | Skill | 7 | today | MIT | A | 54 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |