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 Paydirt-AI/paydirt-mcp --skill install-paydirtgit clone --depth 1 https://github.com/Paydirt-AI/paydirt-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/paydirt-ai/paydirt-mcp/install-paydirt)<a href="https://agentmods.dev/skills/paydirt-ai/paydirt-mcp/install-paydirt"><img src="https://agentmods.dev/badge/skills/paydirt-ai/paydirt-mcp/install-paydirt/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/paydirt-ai/paydirt-mcp/install-paydirt"><img src="https://agentmods.dev/badge/skills/paydirt-ai/paydirt-mcp/install-paydirt.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 | $0.00046 | $0.00666 |
| Opus 5 | $0.00023 | $0.00333 |
| Sonnet 5 | $0.00009 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
install-paydirt 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 7d 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.
What it actually says
Install and operate Paydirt
Inspect the iOS host before setup. Determine its bundle ID, app entry point, dependency manager, subscription source of truth, product IDs, cancellation flow, and requested form placement.
Preserve every existing host-app feedback form, button, screen, handler, destination, and side effect. Never replace, remove, repurpose, or reroute existing feedback behavior unless the user explicitly requests that exact change.
When a public Paydirt remote MCP server is available, confirm one concise form plan before authorization. An explicit request naming the forms counts as confirmation. Otherwise, recommend three clear forms—Suggest a Feature in Settings, Trial Cancellation, and Subscription Cancellation—when subscriptions exist; otherwise explain that cancellation has no trigger and recommend Suggest a Feature. Call paydirt_begin_setup with form_plan_confirmed: true, the selected use cases, and placement; return its authorization URL and call paydirt_finish_setup only after authorization. Browser onboarding handles Google sign-in, app and form creation, and the delivery choice: Slack and coding agents (recommended), Slack only, or coding agents only. The browser discloses that either coding-agent choice includes a read-only daily 9:00 AM Paydirt brief. When Slack is selected, authorize the app owner’s workspace, let them select channels, and verify the requested form assignments before completing setup. Respect the returned delivery preference and do not ask again unless the developer requests a change. Perform every returned host-app action, resolve dependencies, build, and follow ios.install_verification to leave the requested-form setup check visibly open on a simulator or connected device. The developer personally submits every requested form. For Slack, require every requested delivery to reach its selected channel. Separately verify actual cancellation triggers. After all delivery tests pass, create the included daily task with daily_brief.task_prompt when the host supports native scheduling; otherwise report the limitation and provide the prompt without claiming a schedule exists. Slack-only delivery does not include the brief. Digests are read-only and never create coding tasks or edit the app. Agent response access is read-only and must never inject every response into every session or take automatic action. Never submit a test or include the automatic trigger in release builds. Preserve existing purchase and feedback behavior; use RevenueCat when installed and StoreKit otherwise.
For a named form at a screen or action, use paydirt_add_feedback_form, preserve the user's placement exactly, edit that location in the app, and build it. Remote form creation alone is not completion.
Raw questions and answers are authoritative. An AI summary may supplement them. Do not automatically take product or coding action from feedback.
If the remote MCP server is not connected, explain that this submission bundle is intentionally inactive until Paydirt deploys and verifies its public HTTPS MCP endpoint. Do not substitute or describe the npm stdio process as a remote endpoint.
Only completed Q&A is delivered. Never send cancellation-only notices, empty responses, or drafts to Slack.
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.
- 7d ago Changed · +2 lines · +1 tokens per session 51b622b2da1e
- 12d ago First seen · 22 lines · 45 tokens per session scan A f45ab4cd5fd1
install-paydirt is a skill published in the GitHub repository Paydirt-AI/paydirt-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 666 once invoked, about $0.0002 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
analyzing-ios-app-security-with-objection
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
ios-simulator-skill
29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
argent-create-flow
Create, record, edit, replay, or repair reusable Argent flow YAML files. Use when the user asks to record or replay a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-flows. Also use before repeating three or more interactions. For one-off UI checks…
mastg
Autonomous mobile security audit aligned with OWASP MASTG v2. Performs checklist-driven analysis across MASVS categories: storage, crypto, network, platform, code, resilience, privacy. Exports structured markdown report with MASTG test references.
spm-build-analysis
Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode builds. Use when a developer suspects packages, plugins, or dependency graph shape are hurting clean or incremental build performance, mentions SPM slowness, package resolution time, build…