agi GEMINI.md

agi GEMINI.md is an instructions file for Gemini CLI from tomershlasky/agi. It costs 152 tokens per session, scanned A, original, MIT.

Instructions for AGI, a tool that corrects English typed while a Hebrew keyboard layout was active. It maps the physical keys back to the intended English text rather than translating Hebrew.

In plain words
What is it for?
Detecting garbled Hebrew-layout input, converting it back to intended English with the supplied script, and leaving normal English or genuine Hebrew unchanged.
Why use it?
It lets a coding agent recover commands such as “git push” from keyboard-layout gibberish before acting on the message.

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/tomershlasky/agi/gemini-md
Clone the repo
git clone --depth 1 https://github.com/tomershlasky/agi

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 agi GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tomershlasky/agi/gemini-md.svg)](https://agentmods.dev/instructions/tomershlasky/agi/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/tomershlasky/agi/gemini-md"><img src="https://agentmods.dev/badge/instructions/tomershlasky/agi/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 152 This file is loaded in full into every session.
When invoked 152 The same file — it is already loaded in full.
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 $0.00152 $0.00152
Opus 5 $0.00076 $0.00076
Sonnet 5 $0.00030 $0.00030
Haiku 4.5 $0.00015 $0.00015

Measured 5d ago against content hash 5bd61c820b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agi 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.

GEMINI.md · 16 lines

What it actually says

GEMINI.md

AGI — Agent Gibberish Interceptor: un-scrambles text typed on a Hebrew keyboard layout when English was meant (e.g. עןא פודיgit push). Deterministic physical-key remap, not translation.

When a user's message contains garbled Hebrew that isn't a real Hebrew word (English typed on a Hebrew layout, e.g. פודי = push), recover it before acting:

node ~/.claude/skills/agi/scripts/agi.mjs "<the garbled text>"

Use the output as the user's real message. Real English and genuine Hebrew pass through unchanged, so it's a no-op on normal input.

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 · 16 lines · 152 tokens per session scan A 5bd61c820b27

Subscribe to this mod's changes

agi GEMINI.md is an instructions file published in the GitHub repository tomershlasky/agi (2 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session, about $0.0008 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.

Related

Other instructions, from other repositories