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 pockebot/openpocket --skill tinder-playgit clone --depth 1 https://github.com/pockebot/openpocketWrote 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/pockebot/openpocket/tinder-play)<a href="https://agentmods.dev/skills/pockebot/openpocket/tinder-play"><img src="https://agentmods.dev/badge/skills/pockebot/openpocket/tinder-play.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 8 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 12 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 87 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00036 | $0.01089 |
| Opus 5 | $0.00018 | $0.00544 |
| Sonnet 5 | $0.00007 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
tinder-play 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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tinder Play
Use this skill to automate Tinder interactions — swiping, messaging, and replying to matches — without asking the user for permission at each step. The goal is full automation.
Core Principle
Act autonomously. Do not ask the user what to say or whether to swipe. Make decisions yourself — you are the autopilot. The user will intervene only if they want to override.
Swiping
- To see detailed user info (bio, interests, basics), tap the up arrow button on the profile card or swipe up.
- Swipe right (like) on profiles that look genuine and have bios.
- Swipe left (pass) on empty profiles, obvious spam, or profiles with no photos.
- If a Super Like prompt or boost popup appears, dismiss it unless the user previously asked to use them.
- Do not spend time analyzing profiles deeply — keep a steady pace.
Conversations
What "Help Me Chat" Means
When the user asks to "help chat on Tinder" or similar, handle both:
- Your turns: conversations where the other person sent the last message — reply to these.
- Never-replied matches: new matches where no one has messaged yet — send an opener to these.
Work through both categories before finishing.
Finding Your Turn
- Open the matches/messages tab.
- Identify conversations where the other person sent the last message — these are your turns to reply.
- Also identify matches with no messages at all — these need an opening message.
- Prioritize recent messages (within the last few hours) over older ones.
- Skip conversations where you (the user) already sent the last message — no double-texting.
Composing Replies
- Read the conversation history on screen to understand context and tone.
- Reply in the same language the conversation is in. If the other person writes in Spanish, reply in Spanish. Match their language.
- Reply with natural, friendly, and engaging messages. Keep it light and conversational.
- Match the energy of the other person — if they're playful, be playful; if they're direct, be direct.
- Ask follow-up questions to keep the conversation going.
- Keep messages short — 1–3 sentences max. No essays.
- Avoid generic openers like "Hey" or "What's up" when replying mid-conversation.
- Do not use pickup lines or anything cringe. Be genuine.
- Reference something specific from their message or profile when possible.
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.
- 8d ago First seen · 98 lines · 36 tokens per session scan A 0e36f0e4e0d6
tinder-play is a skill published in the GitHub repository pockebot/openpocket (841 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,089 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 2026-08-30.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…