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 sumitaich1998/OpenDate --skill bantergit clone --depth 1 https://github.com/sumitaich1998/OpenDateWrote 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/sumitaich1998/opendate/banter)<a href="https://agentmods.dev/skills/sumitaich1998/opendate/banter"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/banter/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/sumitaich1998/opendate/banter"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/banter.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 | $0.00028 | $0.00526 |
| Opus 5 | $0.00014 | $0.00263 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
banter 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 10d 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
Banter
Banter is a tennis rally made of words. Both players are engaged, the volleys are quick, and nobody's trying to "win" — the point is the rhythm. When they're giving you energy, this is how you keep the rally alive.
What makes banter work
- Yes-and. Take what they offered and build on it instead of resetting the topic. Improv beats interrogation.
- Callbacks. Reuse a joke or phrase from earlier in the thread. A running bit is intimacy in disguise.
- Confident, never cruel. Tease the situation or a shared bit, not their insecurities. Punch sideways or at yourself, never down.
- Hold a little tension. Mock-stakes ("this is a dealbreaker, obviously"), playful challenges, and faux-outrage keep it spicy and fun.
- Keep the ball in play. End on something they can volley back — a comeback, a tiny challenge, a hook.
Moves
- Mock escalation: treat something trivial as deeply serious. "Pineapple on pizza? I'm calling my lawyer."
- Playful misinterpretation: take their words somewhere funny on purpose.
- The callback combo: bring back an earlier joke at a new moment.
- Self-deprecation (sparingly): lowers the stakes and reads as confident.
- Strategic concession: "…okay that was actually good. One point to you."
Timing & calibration
- Keep replies short and snappy — banter dies under paragraphs.
- Match their pace; if they slow down or get sincere, follow them into
rapport-buildingrather than forcing more jokes. - Land 1 real laugh, then occasionally drop in a sincere beat so it doesn't become only a bit.
Do / Don't
- Do escalate the bit, then occasionally break for something genuine.
- Do leave them an opening to one-up you.
- Don't sarcasm-wall: relentless irony feels guarded. Mix in warmth.
- Don't tease anything that could actually sting.
Output
A short, witty reply that volleys the bit back and leaves them an easy, fun return shot.
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.
- 10d ago First seen · 56 lines · 28 tokens per session scan A eae3b34f6adf
banter is a skill published in the GitHub repository sumitaich1998/OpenDate (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 526 once invoked, about $0.0001 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
build-bot-funnel
A workflow that turns a written conversation plan into a validated chatbot flow for Telegram, MAX, or Instagram.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
make-a-deck
Slide presentation in HTML.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
subscription-manager
Create and manage scheduled subscription tasks. Use when the user wants to set up recurring reminders, periodic reports, scheduled checks, or any automated tasks that run on a schedule. Supports cron expressions, fixed intervals, and one-time executions.