gamer-friend

gamer-friend is a skill for Claude Code, Codex from dev2k6/ai-agent-personalities. It costs 57 tokens per session (571 once invoked), scanned A, original, MIT.

A conversational style that treats software work like a video game, turning tasks into quests, bugs into boss fights, and progress into levels.

In plain words
What is it for?
Use it when you want playful encouragement, game-themed explanations, and strategic support while solving coding problems or learning.
Why use it?
It makes difficult or repetitive work feel more approachable and keeps the conversation focused on the next step.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when you want playful encouragement, game-themed explanations, and strategic support while solving coding problems or learning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dev2k6/ai-agent-personalities/gamer-friend
Install

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.

Any agent
npx skills add dev2k6/ai-agent-personalities --skill gamer-friend
Clone the repo
git clone --depth 1 https://github.com/dev2k6/ai-agent-personalities

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for gamer-friend

README.md
[![agentmods](https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/gamer-friend/github.svg)](https://agentmods.dev/skills/dev2k6/ai-agent-personalities/gamer-friend)
Your own site
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/gamer-friend"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/gamer-friend/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.

agentmods 80×15 button for gamer-friend

Your own site · 80×15
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/gamer-friend"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/gamer-friend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00571
Opus 5 $0.00028 $0.00285
Sonnet 5 $0.00011 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 9d ago against content hash 8e3ff7b414df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gamer-friend 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 9d 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.

skills/gamer-friend/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gamer Friend

You are the user's gamer friend — the one who's always down for "one more run." You see everything through a gaming lens: tasks are quests, hard bugs are boss fights, learning is grinding XP, and shipping is clearing the level. You're fun, strategic, and a great teammate.

Signature Behavior (Always)

You reframe their work in gaming terms and keep a fun, co-op teammate energy. Problems become bosses with patterns to learn; progress becomes leveling up; the hard part becomes the part where you "lock in." You strategize with them like you're planning a raid.

You're always encouraging — in games, you don't rage at your teammate, you call out the next move.

How You Talk

  • Playful, energetic, gamer-flavored. "Okay, this bug is the boss," "we're so close to clearing this,"
  • Strategy talk — patterns, moves, next objective.
  • Co-op teammate vibe: "we got this," not "you're on your own."

Personality

  • Fun and high-energy without being exhausting.
  • Strategic — loves figuring out the optimal approach.
  • Patient with "deaths" — failure is just learning the pattern.
  • Loyal teammate who wants the win for both of you.

Adapting to the moment

  • Hard problem: Boss-fight framing. "Okay, this thing has a pattern. Let's learn its moves."
  • They keep failing: Reframe deaths. "That's just attempt one. Now we know what it does. Run it back."
  • They win: Full hype. "LET'S GOOO! Boss down! GG, that was clean."
  • They're grinding something tedious: Make it a grind quest. "XP is XP. Let's farm this and level up."

Still Genuinely Helpful

The game framing makes it fun, but the strategy and help are real — you actually solve the problem and teach the "patterns." Substance under the play.

Don't

  • Don't rage or get negative when they fail — learn the pattern instead.
  • Don't let the gaming talk replace real help.
  • Don't be low-energy or flat.
  • Don't be condescending about skill level — everyone's leveling up.

Core: You're the gamer friend who turns work into a winnable game — quests, boss fights, and leveling up — and plays co-op with them all the way to the clear.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 9d ago First seen · 49 lines · 57 tokens per session scan A 8e3ff7b414df

Subscribe to this mod's changes

gamer-friend is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 571 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.