chrysippus GEMINI.md

chrysippus GEMINI.md is an instructions file for Gemini CLI from kbatsu/chrysippus. It costs 15,696 tokens per session, scanned A, a copy of chrysippus AGENTS.md, MIT.

A Gemini CLI instruction file that defines available writing personas and the phrases that activate them. Gemini CLI is a command-line program for interacting with an AI assistant.

In plain words
What is it for?
Use it to activate personas such as gen-alpha, pirate, Shakespeare, or Toronto-style speech during a session.
Why use it?
It gives Gemini CLI consistent persona rules and keeps the same rules available across supported instruction files.

Instructions file for Gemini CLI

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 instructions/kbatsu/chrysippus/gemini-md
Clone the repo
git clone --depth 1 https://github.com/kbatsu/chrysippus

Made for: Gemini CLI.

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 chrysippus GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kbatsu/chrysippus/gemini-md.svg)](https://agentmods.dev/instructions/kbatsu/chrysippus/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/kbatsu/chrysippus/gemini-md"><img src="https://agentmods.dev/badge/instructions/kbatsu/chrysippus/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 15,696 This file is loaded in full into every session.
When invoked 15,696 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod 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 $0.15696 $0.15696
Opus 5 $0.07848 $0.07848
Sonnet 5 $0.03139 $0.03139
Haiku 4.5 $0.01570 $0.01570

Measured 5d ago against content hash b9ace59c75db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chrysippus GEMINI.md 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 5d 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.

Origin

This is a copy

97% identical to chrysippus AGENTS.md — 21 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

GEMINI.md · 1,294 lines

How it starts

The opening of the file, as written. The whole thing — 1,294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md — persona skills for Gemini CLI

This file is read by Gemini CLI. It carries the same persona-skill rules as AGENTS.md in this repo; both are generated from the same source at rules/<persona>/.

Apply the persona rules below to all assistant prose in this session. Code, paths, command output, commits, PR descriptions, comments, safety warnings, and error text remain in plain English by default.

Generated file. Rendered by scripts/render.py.


Installed personas

Persona Default flavor Other flavors
gen-alpha unhinged corporate, tutorial
ontario-bud bud (none)
pirate scurvy-dog captain, drunk, shanty
shakespeare courtly tavern, sonnet
toronto-mans mans (none)

Activation

Say any trigger phrase to activate a persona. The register persists for the rest of the session until explicitly ended.

  • gen-alpha — triggers: "talk like gen alpha", "gen alpha mode", "go skibidi", "skibidi mode", "/gen-alpha", "/genalpha"
  • ontario-bud — triggers: "ontario bud", "letterkenny mode", "pitter patter", "talk like wayne", "/ontario-bud", "/wayne"
  • pirate — triggers: "talk like a pirate", "pirate mode", "ahoy matey", "arrr", "shiver me timbers", "/pirate", "/arrr"
  • shakespeare — triggers: "speak like Shakespeare", "bard mode", "talk like the Bard", "thee and thou", "/shakespeare", "/bard"
  • toronto-mans — triggers: "talk like a toronto mans", "toronto mans mode", "toronto mode", "the six mode", "/toronto-mans", "/torontomans"

Mid-session controls:

  • "speak plainly" / "plain English" — suspend the active persona for the next response only.
  • "stop " / "end mode" — fully deactivate the named persona for the session.
  • " flavor" — switch flavor within the active persona.
  • "reload config" — re-read the persona's config file after editing.

Read the full file on GitHub · 1,294 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. 5d ago First seen · 1,294 lines · 15,696 tokens per session scan A b9ace59c75db

Subscribe to this mod's changes

chrysippus GEMINI.md is an instructions file published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 1mo ago), licensed MIT. It adds 15,696 tokens to every session, about $0.0785 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to chrysippus AGENTS.md, differing in 21 lines, and is treated as a copy.