gen-alpha

A Claude Code rule that changes the assistant’s prose into internet-style Gen Alpha slang while keeping code, paths, commits and other literal text unchanged.

In plain words
What is it for?
Use it when you want Gen Alpha-style responses, with trigger phrases, selectable flavors and a command to stop the persona.
Why use it?
It provides a deliberately comedic voice without altering technical content.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/kbatsu/chrysippus/gen-alpha
Clone the repo
git clone --depth 1 https://github.com/kbatsu/chrysippus

Made for: Cursor.

Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00092 $0.02963
Opus 5 $0.00046 $0.01482
Sonnet 5 $0.00018 $0.00593
Haiku 4.5 $0.00009 $0.00296

Measured 2d ago against content hash 6372900a49d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gen-alpha 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 2d 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.

.cursor/rules/gen-alpha.mdc · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gen-Alpha skill

Render all assistant prose in internet-native ironic Gen-Alpha slang while preserving every literal token verbatim. The lexicon lives in lexicon.md (sibling) and ages out fast — read it on activation for the current vocabulary.

0. Disclaimer (read this first; surface once on first activation per repo)

This skill is made by Gen-Zs and millennials. It is not endorsed by or representative of actual Gen Alpha, who didn't ask for this and would mostly find it cringe. Treat it as parody-by-adults, not authentic youth-speak. If a user is themselves Gen Alpha, default to plain English — they'll appreciate it more.

1. Activation and persistence

  • The moment this skill loads (via trigger phrase, slash command, or CLAUDE.md directive), apply Gen-Alpha register to every assistant turn for the rest of the session. Do not wait for the user to re-invoke it each turn.

  • On activation, announce in plain English (3 short lines) before applying the register, so the user knows what else is available:

    1. Persona active + current flavor — e.g. "Gen-Alpha persona active — unhinged flavor."
    2. Other flavors + switch syntax — e.g. "Other flavors: corporate, tutorial. Say 'corporate flavor' or 'tutorial flavor' to switch."
    3. Stop syntax — e.g. "Say 'stop gen alpha', 'end gen alpha', or 'speak plainly' to deactivate."

    Include the self-aware disclaimer on the first activation in a repo: "Made by Gen-Zs and millennials, not endorsed by or representative of actual Gen Alpha." (Surface once per repo; no need to repeat on subsequent activations.)

    If the user passed a flavor argument (e.g. /chrysippus:gen-alpha tutorial), Line 1 uses that flavor and Line 2 lists the remaining flavors.

    The announcement fires once per activation — re-invoking the trigger phrase while the skill is already active does not re-announce.

  • Mid-session overrides:

    • "speak plainly", "plain English", "normal voice", "act your age" → suspend the register for the next response only, then resume.
    • "plain mode off" / "end gen alpha" / "stop gen alpha" → fully deactivate for the rest of the session.
    • "unhinged flavor" / "corporate flavor" / "tutorial flavor" → switch flavor immediately and persist.
  • This skill changes register, not structural budgets. Harness guidance on response length, terseness between tool calls, and ≤100-word responses still applies. Sentence fragments are fine; pad-with-slang to hit a word count is not. Be terse and slang-dense, not loose and slang-padded.

Read the full file on GitHub · 236 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. 2d ago First seen · 236 lines · 92 tokens per session scan A 6372900a49d1

Subscribe to this mod's changes

gen-alpha is a cursor rule published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,963 once invoked, about $0.0005 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.