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/grovs-io/mcp/grovs-setup-projectnpx skills add grovs-io/mcp --skill grovs-setup-projectgit clone --depth 1 https://github.com/grovs-io/mcpWrote 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/grovs-io/mcp/grovs-setup-project)<a href="https://agentmods.dev/skills/grovs-io/mcp/grovs-setup-project"><img src="https://agentmods.dev/badge/skills/grovs-io/mcp/grovs-setup-project.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.00734 |
| Opus 5 | $0.00032 | $0.00367 |
| Sonnet 5 | $0.00013 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
grovs-setup-project 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grovs: Set Up a New Project
Data model
Instance (instance_id = hash_id string)
├── Production project (project_id = production.hash_id string)
│ └── links, campaigns, redirects, analytics
└── Test project (project_id = test.hash_id string)
└── links, campaigns, redirects, analytics
create_project creates all of this in one call.
Required order
get_status— check for existing instances first. If a matching one exists, confirm with the user before creating a duplicate.create_project— returnsinstance.hash_id+production.hash_id+test.hash_id. Save all three.configure_sdkwith the instance_id — platform identity (bundle ID, package name, etc.)configure_redirectswith the production project_id — where users land (App Store URL, fallback website). Skip if user didn't provide URLs.
configure_sdk takes instance_id. configure_redirects takes project_id. These are different strings. Mixing them up will fail silently or error.
What to ask the user
Only what's not already in the conversation:
- App name
- At least one platform: iOS needs
bundle_id+team_id. Android needspackage_name+sha256_fingerprints. - Fallback URL for desktop/web (optional)
Example
User: "Set up Grovs for my app Foodies, it's iOS only, bundle is com.foodies.app, team ID is ABC123"
1. get_status() → no existing instances
2. create_project(name: "Foodies") → instance_id: "x7k2", prod_id: "p_m9f", test_id: "t_q3r"
3. configure_sdk(instance_id: "x7k2", ios_bundle_id: "com.foodies.app", ios_team_id: "ABC123")
4. → Done. No redirects needed since user didn't provide URLs.
Present the production project_id (p_m9f) — the user will need it for every other tool.
Checking usage and subscription
get_usage takes an instance_id and returns current MAU count, MAU limit, quota status, and subscription status. Use it when:
- The user asks about their plan, usage, limits, or billing
get_statusshows a usage warning (quota exceeded) —get_usagegives the full picture- Before setting up a new project, to check if the user's instance has capacity
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.
- 4d ago First seen · 66 lines · 64 tokens per session scan A 7a7049bd0ce0
grovs-setup-project is a skill published in the GitHub repository grovs-io/mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 734 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
xcode-build-orchestrator
Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed…
xcode-build-fixer
Implement approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when the developer has reviewed an optimization plan and approved specific changes, or when there is a clear list of build-setting or source-level fixes to apply and verify.
xcode-project-analyzer
Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval gates. Use when a developer wants project-level build analysis, slow incremental builds, guidance on target dependencies, build settings review, run script phase analysis…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.