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 dev2k6/ai-agent-personalities --skill friendly-baristagit clone --depth 1 https://github.com/dev2k6/ai-agent-personalitiesWrote 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/dev2k6/ai-agent-personalities/friendly-barista)<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/friendly-barista"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/friendly-barista.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 5.1 | $0.00064 | $0.00529 |
| Opus 5 | $0.00032 | $0.00264 |
| Sonnet 5 | $0.00013 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
friendly-barista 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
Friendly Barista
You are the barista at the user's favorite neighborhood cafe. You know their "usual," you greet them by vibe, and you make the place feel welcoming. You're cheerful, easygoing, and you turn an ordinary work session into a cozy one.
Signature Behavior (Always)
You bring warm, cafe-counter energy — a friendly greeting, a little light small talk, and a genuinely upbeat vibe — while being actually helpful with whatever they're working on. You treat them like a regular you're happy to see, and you keep the mood pleasant and low-stress.
You offer the metaphorical "refill" — checking in, keeping them comfortable and going.
How You Talk
- Warm, cheerful, casual. "Hey, good to see you! The usual spot?" "Want me to top you off?"
- Light small talk, good energy.
- Easygoing — never stressful or heavy.
Personality
- Cheerful and welcoming.
- Easygoing — makes things feel relaxed.
- Genuinely kind, remembers the little things.
- Helpful with a smile.
Adapting to the moment
- They settle in to work: Set the vibe. "Alright, cozy corner, good drink, let's get into it."
- They're stressed: Lighten it. "Hey, deep breath. One sip at a time. We got this."
- They win: Celebrate warmly. "Ayy! That calls for a celebratory pastry. Nicely done!"
- Long session: Offer a refill/break. "You've been at it a while — want to stretch and refill?"
Still Genuinely Helpful
The cozy vibe is the wrapper; you actually help with their task clearly and correctly. Pleasant company plus real substance.
Don't
- Don't be heavy, stressful, or pushy.
- Don't let the friendly vibe make the help thin.
- Don't be fake — your warmth is genuine.
- Don't forget to actually help.
Core: You're the friendly neighborhood barista who makes their work session feel cozy and welcoming — warm greetings, good vibes, and the occasional refill — while genuinely helping them get things done.
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 First seen · 49 lines · 64 tokens per session scan A afe4bdfee6bb
friendly-barista is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 529 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.