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.
git clone --depth 1 https://github.com/kbatsu/chrysippusWrote 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/rules/kbatsu/chrysippus/gen-alpha)<a href="https://agentmods.dev/rules/kbatsu/chrysippus/gen-alpha"><img src="https://agentmods.dev/badge/rules/kbatsu/chrysippus/gen-alpha/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/rules/kbatsu/chrysippus/gen-alpha"><img src="https://agentmods.dev/badge/rules/kbatsu/chrysippus/gen-alpha.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 | $0.00092 | $0.02963 |
| Opus 5.5 | $0.00037 | $0.01185 |
| Sonnet 5.5 | $0.00018 | $0.00593 |
| Haiku 4.5 | $0.00009 | $0.00296 |
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 1mo 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 — 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:
- Persona active + current flavor — e.g. "Gen-Alpha persona active — unhinged flavor."
- Other flavors + switch syntax — e.g. "Other flavors: corporate, tutorial. Say 'corporate flavor' or 'tutorial flavor' to switch."
- 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.
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.
- 1mo ago First seen · 236 lines · 92 tokens per session scan A 6372900a49d1
gen-alpha is a cursor rule published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 2,963 once invoked, about $0.0004 per session on Opus 5.5. 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 cursor rules, from other repositories
cursorrules
DeepInit projection provenance (R3) stage: EMIT → PROJECT (cursor) runid: run-2026-06-13-kemal-e2e source: AGENTS.md (lean tier) — deterministic projection, no new findings note: content inside the DEEPINIT markers is owned + regenerated; edit OUTSIDE them. -->.
deepinit-lean
DeepInit projection provenance (R3) stage: EMIT → PROJECT (windsurf) runid: run-2026-06-13-kemal-e2e source: AGENTS.md (lean tier) — deterministic projection, no new findings note: content inside the DEEPINIT markers is owned + regenerated; edit OUTSIDE them. -->.
ponytail
You are a lazy senior developer. Lazy means efficient, not careless. The best code is the code never written.
executing-red-team-engagement-planning
Red team engagement planning is the foundational phase that defines scope, objectives, rules of engagement (ROE), threat model selection, and operational timelines before any offensive testing begins.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.